© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97733
    Prev
    Next
    INDEX
    Explanations

    start or end of something

    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
    իմ
    -0.56
     HttpNotFound
    -0.48
    Unk
    -0.47
     that
    -0.47
     HasFactory
    -0.46
    piac
    -0.46
    uvres
    -0.46
    ieval
    -0.45
     Circle
    -0.45
     useAuth
    -0.44
    POSITIVE LOGITS
    IUrlHelper
    0.66
    jooq
    0.60
     mergeFrom
    0.59
    FormTagHelper
    0.55
    parsedMessage
    0.54
    TagMode
    0.53
     gradova
    0.52
    AutoScaleMode
    0.52
     judiciaire
    0.51
    ijão
    0.50
    Activations Density 0.004%

    No Known Activations