© 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. 1987
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    
    -0.73
     defaultstate
    -0.63
    TypedDataSet
    -0.63
    TagMode
    -0.63
     kaarangay
    -0.61
     sasa
    -0.61
    Vidite
    -0.59
    GraphicsUnit
    -0.59
     Now
    -0.57
    IndentedString
    -0.55
    POSITIVE LOGITS
     when
    0.68
     shortly
    0.57
     ever
    0.57
     long
    0.56
     出版
    0.56
     and
    0.52
     later
    0.51
     back
    0.49
     purchasing
    0.49
     przet
    0.49
    Activations Density 0.010%

    No Known Activations