© 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. 4-CLT-HP
    7. 34
    Prev
    Next
    INDEX
    Explanations

    own

    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
    skosten
    -0.54
    '},
    -0.47
     برانيه
    -0.47
    cinoma
    -0.46
    brunn
    -0.46
     bpy
    -0.46
    VOA
    -0.46
    lesque
    -0.45
    EXPERIMENT
    -0.45
    Interview
    -0.45
    POSITIVE LOGITS
    Personensuche
    0.65
     nahilalakip
    0.60
     OMITBAD
    0.58
    Xna
    0.55
    tia
    0.54
    Maker
    0.52
    ⓧ
    0.51
     الحره
    0.50
    RTSC
    0.50
     AssemblyProduct
    0.50
    Activations Density 0.014%

    No Known Activations