© 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. 40043
    Prev
    Next
    INDEX
    Explanations

    custom

    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
     custom
    -0.98
     
    -0.82
     I
    -0.76
     (
    -0.75
    ,
    -0.74
     and
    -0.71
     start
    -0.71
     us
    -0.71
     or
    -0.70
     in
    -0.69
    POSITIVE LOGITS
     Houſe
    1.58
     houſe
    1.55
     ―――――
    1.55
     pleaſure
    1.55
     myſelf
    1.55
     Jefus
    1.54
     doubtnut
    1.52
     ་་
    1.51
     itſelf
    1.51
     preſent
    1.49
    Activations Density 0.495%

    No Known Activations