Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12631
    Prev
    Next
    INDEX
    Explanations

    us

    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
    us
    -0.91
     itſelf
    -0.84
    i
    -0.75
    a
    -0.69
    e
    -0.64
    usza
    -0.63
     myſelf
    -0.63
     themſelves
    -0.63
     invokingState
    -0.58
    RetentionPolicy
    -0.58
    POSITIVE LOGITS
     utafitiHapana
    0.52
    -------
    0.48
    antMatchers
    0.48
    pheric
    0.46
    aume
    0.46
    prar
    0.45
    γη
    0.45
    тельстве
    0.45
    Amos
    0.45
     sī
    0.44
    Activations Density 0.024%

    No Known Activations