© 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. 5-CLT-HP
    7. 92747
    Prev
    Next
    INDEX
    Explanations

    broken or separated

    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
     Cline
    -0.51
    inete
    -0.50
     Rojas
    -0.49
    idhi
    -0.48
     PHASE
    -0.48
     xí
    -0.48
    Spaces
    -0.48
     eingestellt
    -0.47
    chaus
    -0.47
    NOS
    -0.46
    POSITIVE LOGITS
    CloseOperation
    0.86
     kasarigan
    0.80
     مشين
    0.76
    ReusableCell
    0.73
    principalColumn
    0.68
     initComponents
    0.66
    存于互联网档案馆
    0.63
    RectangleBorder
    0.63
     off
    0.58
    DockStyle
    0.56
    Activations Density 0.001%

    No Known Activations