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. 435
    Prev
    Next
    INDEX
    Explanations

    over

    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
    <bos>
    -0.63
    LookAnd
    -0.60
     Reverso
    -0.59
     Armenians
    -0.58
    íncia
    -0.56
     millennia
    -0.54
    angeran
    -0.53
     Montmartre
    -0.52
    salms
    -0.52
    cèse
    -0.52
    POSITIVE LOGITS
    ]")]
    0.62
    heads
    0.61
     setuptools
    0.61
    Hozzáférés
    0.54
     UIImageView
    0.53
     ✭✭
    0.52
     zipper
    0.47
    InSection
    0.47
    DoubleQuotes
    0.47
    ViewImports
    0.46
    Activations Density 0.051%

    No Known Activations