© 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. 0-CLT-HP
    7. 94435
    Prev
    Next
    INDEX
    Explanations

    reporting

    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
    .
    -0.56
     if
    -0.52
    ;
    -0.51
    ’
    -0.50
     to
    -0.49
     is
    -0.47
    if
    -0.47
    is
    -0.47
    :
    -0.46
     Y
    -0.45
    POSITIVE LOGITS
     Efq
    1.07
     itſelf
    1.06
     myſelf
    1.00
    Datuak
    0.98
    RenderAtEndOf
    0.96
     themſelves
    0.95
     raiſ
    0.94
     Reſ
    0.91
     ſeveral
    0.91
     Monfieur
    0.91
    Activations Density 0.376%

    No Known Activations