© 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. Gemma-2-2B
    5. 0-CLT-HP
    7. 41796
    Prev
    Next
    INDEX
    Explanations

    able

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     was
    -0.93
    Was
    -0.84
     wasn
    -0.79
    was
    -0.77
     Was
    -0.77
    était
    -0.77
    wasn
    -0.71
    twas
    -0.66
     wasnt
    -0.66
     Wasn
    -0.65
    POSITIVE LOGITS
    ^(@)
    0.76
     are
    0.65
     have
    0.62
    <bos>
    0.60
     auffi
    0.60
    DockStyle
    0.59
    hematical
    0.58
    CompleteListener
    0.57
     Tienen
    0.57
    Życiorys
    0.56
    Activations Density 0.092%

    No Known Activations