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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12878
    Prev
    Next
    INDEX
    Explanations

    0

    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
     myſelf
    -1.20
     Monfieur
    -1.09
     pleaſure
    -1.06
     themſelves
    -1.00
    <bos>
    -0.97
     Shakspeare
    -0.95
     purpoſe
    -0.94
     Efq
    -0.94
     itſelf
    -0.93
     himſelf
    -0.92
    POSITIVE LOGITS
     }^{
    0.47
    ]<=
    0.47
     }_{
    0.46
    ној
    0.45
     
    0.44
    ocer
    0.43
    ⎩
    0.43
    __[
    0.42
    <eos>
    0.41
     thức
    0.41
    Activations Density 0.264%

    No Known Activations