© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 318
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Tam" with high activation values

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1437
    +0.09
    0.3%
    1413
    +0.09
    0.3%
    1416
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.03
    1120
    +0.09
    0.03
    690
    +0.08
    0.02
    Negative Logits
     picante
    -0.63
     barbacoa
    -0.62
     asado
    -0.61
    bài
    -0.59
    tổng
    -0.59
     jakieś
    -0.58
    Trả
    -0.56
    Trước
    -0.56
     win
    -0.55
    các
    -0.55
    POSITIVE LOGITS
     Tam
    3.21
    Tam
    3.01
     tam
    2.42
     TAM
    1.98
    TAM
    1.73
    tam
    1.63
     tamper
    1.43
    tamp
    1.33
     habile
    1.22
     Tamp
    1.13
    Activations Density 0.223%

    No Known Activations