© 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. 94195
    Prev
    Next
    INDEX
    Explanations

    proteins

    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
     Ray
    -0.92
    TagMode
    -0.80
     ray
    -0.80
    DrawerToggle
    -0.69
     RAY
    -0.66
    fortun
    -0.65
    /*
    -0.61
    HasAnnotation
    -0.61
    sociation
    -0.59
    andafter
    -0.59
    POSITIVE LOGITS
     habet
    0.64
     juridiques
    0.60
    rizona
    0.56
     batterie
    0.54
     Numa
    0.54
    buttonBar
    0.52
     ſche
    0.52
     femeninos
    0.52
     purpoſe
    0.52
     domésticos
    0.52
    Activations Density 0.033%

    No Known Activations