© 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. 5-CLT-HP
    7. 1041
    Prev
    Next
    INDEX
    Explanations

    arms

    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
    SequentialGroup
    -1.13
     myſelf
    -0.93
    contentLoaded
    -0.91
     Efq
    -0.90
     CanadaChoose
    -0.87
     doubtnut
    -0.84
    ">:
    -0.84
     itſelf
    -0.83
     Majefty
    -0.83
     IBRARY
    -0.83
    POSITIVE LOGITS
     or
    0.40
     vendre
    0.39
     tiros
    0.38
     bě
    0.38
    šanai
    0.37
     bruk
    0.37
     encuent
    0.37
     pull
    0.34
     naturelles
    0.34
     extérieures
    0.34
    Activations Density 0.002%

    No Known Activations