© 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. 76471
    Prev
    Next
    INDEX
    Explanations

    Technical language

    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
    QMetaType
    -0.73
    ThroughAttribute
    -0.68
     ProtoMessage
    -0.64
     nahilalakip
    -0.63
     تضيفلها
    -0.56
    SpringBootTest
    -0.55
     snippetHide
    -0.54
    GOTREF
    -0.54
    createClass
    -0.53
    ագրություններ
    -0.53
    POSITIVE LOGITS
    setopt
    0.50
     mev
    0.47
     linkovi
    0.46
    ")==
    0.45
    urcht
    0.45
    GEBURTS
    0.44
    PLANATION
    0.43
     Spiral
    0.43
    ictwa
    0.42
     onBind
    0.42
    Activations Density 0.000%

    No Known Activations