© 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. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6224
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numeric thresholds or measurements related to genetic deletions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sikkert
    -0.57
    gjenge
    -0.55
    noinspection
    -0.54
    gnum
    -0.50
    Personendaten
    -0.49
     långt
    -0.48
    gestone
    -0.48
     dacht
    -0.48
     onAnimation
    -0.47
    ynomial
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.85
    DoubleQuotes
    0.65
     four
    0.63
    four
    0.59
    RepeatedField
    0.58
     nahilalakip
    0.57
     BrowserModule
    0.57
    втра
    0.56
    tonode
    0.56
    三种
    0.56
    Activations Density 0.807%

    No Known Activations