© 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. 5-CLT-HP
    7. 5196
    Prev
    Next
    INDEX
    Explanations

    descriptive language

    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
    <eos>
    -0.52
     caros
    -0.49
    vy
    -0.48
    !
    -0.48
    ::
    -0.47
    <bos>
    -0.46
    \\
    -0.45
    idex
    -0.45
    <unused60>
    -0.45
    ins
    -0.45
    POSITIVE LOGITS
     contextLoads
    0.68
     itſelf
    0.66
    EndGlobalSection
    0.65
    Vidite
    0.63
     MainAxisSize
    0.63
    AntiForgeryToken
    0.60
    contentLoaded
    0.59
     Superhost
    0.59
     >=",
    0.59
    NameInMap
    0.58
    Activations Density 0.002%

    No Known Activations