© 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. 42441
    Prev
    Next
    INDEX
    Explanations

    family

    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
     ProtoMessage
    -0.76
     kasarigan
    -0.67
    AddTagHelper
    -0.66
     typelib
    -0.65
    TypedDataSet
    -0.65
    rungsseite
    -0.64
    RUnlock
    -0.64
     Administrativna
    -0.63
    WriteTagHelper
    -0.62
     getItemId
    -0.62
    POSITIVE LOGITS
     spent
    0.57
    '
    0.56
    ii
    0.55
    ’
    0.53
    ‏‏
    0.53
     unaff
    0.52
     was
    0.51
     wasn
    0.50
    ing
    0.49
    ようになりました
    0.48
    Activations Density 0.059%

    No Known Activations