© 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. 14776
    Prev
    Next
    INDEX
    Explanations

    metallic

    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
    metallic
    -1.09
     Metallic
    -1.03
    Metallic
    -0.99
     metallic
    -0.95
    parsedMessage
    -0.73
     ModelExpression
    -0.66
    cyclist
    -0.66
    RTCK
    -0.65
     propOrder
    -0.65
    theless
    -0.63
    POSITIVE LOGITS
    s
    0.74
     JAXBElement
    0.40
     fais
    0.39
     sav
    0.39
    LookAnd
    0.39
     bio
    0.38
    saraba
    0.38
     bonds
    0.37
    ほうが
    0.37
     ste
    0.36
    Activations Density 0.010%

    No Known Activations