© 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. 93857
    Prev
    Next
    INDEX
    Explanations

    fabricated

    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
     فريبيس
    -0.95
     manufactured
    -0.93
    IsMutable
    -0.92
     manufacture
    -0.90
     Monfieur
    -0.84
    ContentAsync
    -0.81
     fabricated
    -0.81
     חיצוניים
    -0.79
     doInBackground
    -0.79
    fabricated
    -0.79
    POSITIVE LOGITS
    .
    0.57
     in
    0.56
    ,
    0.54
    ic
    0.51
    l
    0.50
    ers
    0.49
    n
    0.49
    !
    0.48
     the
    0.47
    li
    0.47
    Activations Density 0.154%

    No Known Activations