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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13460
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal offenses and penalties

    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
    1553
    +0.10
    0.3%
    453
    +0.09
    0.2%
    1648
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.10
    0.03
    1553
    +0.09
    0.04
    417
    +0.07
    0.03
    Negative Logits
     Anm
    -0.71
     fign
    -0.67
     prodi
    -0.67
     idyl
    -0.66
     thut
    -0.66
     Forder
    -0.66
     pessi
    -0.66
     haer
    -0.65
     „,
    -0.64
    astéro
    -0.64
    POSITIVE LOGITS
     penalties
    0.62
    alties
    0.56
     penalty
    0.52
     fines
    0.48
     punishable
    0.48
     imprisonment
    0.48
     Penalties
    0.47
     offerts
    0.46
     felony
    0.46
    sightly
    0.45
    Activations Density 0.134%

    No Known Activations