© 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. 20-CLT-HP
    7. 77695
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · 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
    all
    -0.55
    WritableDatabase
    -0.51
    footer
    -0.50
     defaultstate
    -0.49
     bezeichneter
    -0.46
    local
    -0.46
    ard
    -0.45
     fand
    -0.44
    mette
    -0.44
     resourceCulture
    -0.44
    POSITIVE LOGITS
    forChild
    0.63
    copg
    0.59
    /**
    0.57
    Становништво
    0.57
    ⓧ
    0.57
    Chham
    0.56
    rhosis
    0.54
    مصادر
    0.53
    Посилання
    0.53
    /*
    0.53
    Activations Density 0.000%

    No Known Activations