© 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. 43111
    Prev
    Next
    INDEX
    Explanations

    code/scientific formatting

    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
    ed
    -0.45
    Vezi
    -0.42
     mặt
    -0.41
    :
    -0.41
     on
    -0.41
    rr
    -0.41
     we
    -0.40
    ボン
    -0.40
    étant
    -0.40
    stru
    -0.39
    POSITIVE LOGITS
    OGND
    0.91
    Personensuche
    0.89
    
    0.85
     bezeichneter
    0.82
     RemoteException
    0.81
     BoxDecoration
    0.79
    extAlignment
    0.74
    endphp
    0.73
     HomeComponent
    0.73
    новниш
    0.71
    Activations Density 0.421%

    No Known Activations