© 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. 1-CLT-HP
    7. 9707
    Prev
    Next
    INDEX
    Explanations

    URLs and code

    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
    expandindo
    -0.79
    NameInMap
    -0.73
    writeFieldEnd
    -0.67
    LLocation
    -0.65
    parsedMessage
    -0.64
    GEBURTSDATUM
    -0.61
    ressible
    -0.56
    EndInit
    -0.56
    redients
    -0.56
     otomatig
    -0.55
    POSITIVE LOGITS
    ns
    0.62
    p
    0.59
    index
    0.55
    n
    0.52
    po
    0.49
    ds
    0.49
    d
    0.49
    us
    0.49
    ts
    0.48
    sm
    0.48
    Activations Density 0.306%

    No Known Activations