© 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. 45286
    Prev
    Next
    INDEX
    Explanations

    visiting locations

    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
    Visiting
    -0.98
     Visiting
    -0.89
     visiting
    -0.84
    ba
    -0.80
    visiting
    -0.80
    s
    -0.70
    bu
    -0.66
    bled
    -0.59
    stop
    -0.59
    kan
    -0.58
    POSITIVE LOGITS
     purpoſe
    0.83
    ükemmel
    0.78
     ſind
    0.76
     Majefty
    0.75
     iſt
    0.74
    iented
    0.69
     photolibrary
    0.69
     ſtate
    0.68
    pportun
    0.66
    ^(@)
    0.65
    Activations Density 0.254%

    No Known Activations