© 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. 95180
    Prev
    Next
    INDEX
    Explanations

    to

    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
     nor
    -0.58
    ̣i
    -0.54
     FetchType
    -0.54
    complexContent
    -0.53
    TestBed
    -0.52
     let
    -0.50
    ::<
    -0.50
    ouille
    -0.50
     وقد
    -0.49
     близько
    -0.49
    POSITIVE LOGITS
    anything
    0.86
     anyone
    0.85
     anything
    0.83
     Anything
    0.79
    Anything
    0.74
    anyone
    0.73
     most
    0.72
     anybody
    0.70
     ANYONE
    0.68
     Anybody
    0.67
    Activations Density 0.011%

    No Known Activations