© 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. 42351
    Prev
    Next
    INDEX
    Explanations

    ive

    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
    arsis
    -0.55
     väli
    -0.52
    Pyx
    -0.52
     rage
    -0.49
    FieldBuilder
    -0.49
     aggression
    -0.48
    camento
    -0.47
    之間
    -0.47
     plexus
    -0.47
    ArgsConstructor
    -0.46
    POSITIVE LOGITS
    DockStyle
    0.91
    oa̍t
    0.76
     cherchés
    0.68
     mergeFrom
    0.66
    SequentialGroup
    0.66
    IUrlHelper
    0.64
    jsii
    0.64
    WebServlet
    0.63
    DebuggerStep
    0.60
    IVEREF
    0.60
    Activations Density 0.113%

    No Known Activations