© 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. 0-CLT-HP
    7. 44202
    Prev
    Next
    INDEX
    Explanations

    ask

    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
     ask
    -0.97
    Ask
    -0.90
     Ask
    -0.81
    ask
    -0.60
     ASK
    -0.58
     fråga
    -0.52
     pergunt
    -0.51
    aults
    -0.49
    ASK
    -0.49
     preguntar
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.97
    AccessorTable
    0.97
     ModelExpression
    0.91
    TagMode
    0.91
     Signalez
    0.90
    parsedMessage
    0.89
     itſelf
    0.82
     themſelves
    0.81
     himſelf
    0.80
     Reſ
    0.80
    Activations Density 0.201%

    No Known Activations