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. 91383
    Prev
    Next
    INDEX
    Explanations

    rein

    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
    in
    -1.41
     in
    -0.79
    In
    -0.68
    at
    -0.68
    of
    -0.68
    per
    -0.67
    IN
    -0.66
    out
    -0.63
     In
    -0.60
    as
    -0.59
    POSITIVE LOGITS
     myſelf
    1.01
     Efq
    1.00
     itſelf
    0.99
     themſelves
    0.97
     Jefus
    0.96
     Theſe
    0.94
     himſelf
    0.90
     theſe
    0.85
     becauſe
    0.83
     purpoſe
    0.83
    Activations Density 0.083%

    No Known Activations