© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97714
    Prev
    Next
    INDEX
    Explanations

    scientific procedures

    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
     kanyang
    -0.70
     تضيفلها
    -0.63
     تانيه
    -0.60
    "]];
    -0.59
     للمعارف
    -0.58
     fallu
    -0.57
    .";
    -0.57
     Arxivat
    -0.57
     newOwner
    -0.57
     tillegg
    -0.56
    POSITIVE LOGITS
     the
    1.60
    <bos>
    1.34
     a
    1.15
     their
    1.12
     an
    1.08
     some
    0.94
     this
    0.93
     our
    0.93
     those
    0.93
     it
    0.92
    Activations Density 0.116%

    No Known Activations