© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13215
    Prev
    Next
    INDEX
    Explanations

    rating

    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
    astify
    -0.58
    <bos>
    -0.56
     pinulongan
    -0.52
    хьтан
    -0.52
    Unnamed
    -0.51
    awtextra
    -0.47
    rxjs
    -0.47
     rating
    -0.47
    ucas
    -0.47
     للاسماء
    -0.46
    POSITIVE LOGITS
    parsedMessage
    0.87
    IBOutlet
    0.56
    MLLoader
    0.56
    encodeWith
    0.55
    forName
    0.53
    новништво
    0.53
    AnchorTagHelper
    0.52
     regeringen
    0.52
     SwitchCompat
    0.52
     RemoteException
    0.52
    Activations Density 0.133%

    No Known Activations