© 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. 91401
    Prev
    Next
    INDEX
    Explanations

    April

    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
    enumii
    -0.48
    "]]
    -0.45
     thanks
    -0.45
     seb
    -0.43
    owol
    -0.43
    nextNode
    -0.43
     up
    -0.42
    ார்
    -0.42
    tagHelperRunner
    -0.41
     Thanks
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    0.63
    RepeatedField
    0.61
     nahilalakip
    0.59
     ProtoMessage
    0.56
    lido
    0.56
    ligo
    0.56
    elemField
    0.55
    NonQuery
    0.54
     mergeFrom
    0.54
    ProgressHUD
    0.52
    Activations Density 0.001%

    No Known Activations