© 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. 95070
    Prev
    Next
    INDEX
    Explanations

    fasteners or lines

    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
    ing
    -0.65
    .
    -0.59
     t
    -0.59
     to
    -0.58
     hall
    -0.57
    a
    -0.57
     traits
    -0.56
     (
    -0.55
    <eos>
    -0.55
     in
    -0.54
    POSITIVE LOGITS
     myſelf
    1.55
     Theſe
    1.44
     Monfieur
    1.38
     Reſ
    1.37
     Efq
    1.37
     ―――――
    1.35
     pleaſure
    1.34
     Majefty
    1.31
     ſeveral
    1.30
    ſelf
    1.28
    Activations Density 0.356%

    No Known Activations