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. 0-CLT-HP
    4. 116
    Prev
    Next
    INDEX
    Explanations

    fuller

    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
     Theſe
    -0.94
     itſelf
    -0.93
     Houſe
    -0.91
     Diſ
    -0.87
     Anſ
    -0.87
     myſelf
    -0.86
     Pallas
    -0.84
     Beſ
    -0.81
     Monfieur
    -0.81
     ſeveral
    -0.79
    POSITIVE LOGITS
    d
    0.69
    b
    0.59
    p
    0.55
    t
    0.53
    n
    0.51
    s
    0.50
    v
    0.50
    son
    0.49
    h
    0.49
    ss
    0.48
    Activations Density 0.471%

    No Known Activations