© 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. 91893
    Prev
    Next
    INDEX
    Explanations

    code

    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
    InitVars
    -0.69
     Gazetteer
    -0.67
    ContentAsync
    -0.66
    localctx
    -0.61
    UnusedPrivate
    -0.60
    Collegamenti
    -0.59
    DoubleQuotes
    -0.56
    DockStyle
    -0.55
    rylic
    -0.54
    Reprints
    -0.53
    POSITIVE LOGITS
    selaer
    0.46
     close
    0.46
     ALTERN
    0.46
    JAB
    0.41
    GLenum
    0.41
     Bond
    0.40
    !("{
    0.40
     člá
    0.40
     pleasure
    0.40
     Lawrence
    0.40
    Activations Density 0.005%

    No Known Activations