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. 44783
    Prev
    Next
    INDEX
    Explanations

    or

    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
     pleaſure
    -0.88
     itſelf
    -0.88
     houſe
    -0.84
    ſelves
    -0.83
     myſelf
    -0.83
     ſche
    -0.82
    ſelf
    -0.79
     purpoſe
    -0.78
     Efq
    -0.77
     himſelf
    -0.76
    POSITIVE LOGITS
    ,
    1.21
     it
    0.89
     if
    0.77
    :
    0.75
     he
    0.69
     even
    0.68
    !
    0.65
     you
    0.64
    ?
    0.62
    ,
    0.62
    Activations Density 0.029%

    No Known Activations