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. 91631
    Prev
    Next
    INDEX
    Explanations

    utilized

    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
    ae
    -0.67
    AE
    -0.59
    æ
    -0.55
    hae
    -0.47
    nae
    -0.47
     utilised
    -0.46
    вания
    -0.46
    سة
    -0.45
    ी
    -0.44
    <bos>
    -0.44
    POSITIVE LOGITS
     hâte
    0.93
     iſt
    0.87
     Efq
    0.86
    ſelf
    0.85
     समीक्षाओं
    0.83
    >\<^
    0.83
    ."));
    0.83
     muualla
    0.82
    numerusform
    0.81
    elry
    0.80
    Activations Density 0.277%

    No Known Activations