© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 10645
    Prev
    Next
    INDEX
    Explanations

    details related to a criminal investigation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    814
    +0.08
    0.2%
    1581
    +0.08
    0.2%
    341
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1079
    +0.08
    0.01
    1705
    +0.08
    0.04
    341
    +0.08
    0.03
    Negative Logits
    nang
    -0.44
    ndry
    -0.44
    hef
    -0.43
     suporta
    -0.42
    mycompany
    -0.41
    inkl
    -0.41
     controla
    -0.40
     esconde
    -0.40
     volunte
    -0.40
     abstrait
    -0.38
    POSITIVE LOGITS
     path
    0.91
     getPath
    0.87
    path
    0.82
     paths
    0.81
    paths
    0.78
     Path
    0.72
    Path
    0.68
     tricot
    0.67
     pathway
    0.66
    trajectory
    0.63
    Activations Density 0.317%

    No Known Activations