© 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. 90996
    Prev
    Next
    INDEX
    Explanations

    vitro

    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
    DoubleQuotes
    -0.66
    uxxxx
    -0.61
     Signalez
    -0.60
    SourceChecksum
    -0.60
    principalTable
    -0.58
    TagMode
    -0.57
    ValueStyle
    -0.57
    IContainer
    -0.55
    GEBURTSDATUM
    -0.55
    SequentialGroup
    -0.54
    POSITIVE LOGITS
     litté
    0.61
     〈
    0.60
     صوتيه
    0.57
     Græ
    0.57
    stdafx
    0.56
     ſeveral
    0.56
    cape
    0.56
     ;
    0.56
     Mahmud
    0.55
     Dostupné
    0.55
    Activations Density 0.400%

    No Known Activations