© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45097
    Prev
    Next
    INDEX
    Explanations

    comparisons and ranges

    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
     mentiras
    -0.46
     incluidas
    -0.45
     gång
    -0.43
     and
    -0.43
     mellett
    -0.42
    <b>
    -0.42
     These
    -0.42
    ↵↵
    -0.41
     deur
    -0.41
     compared
    -0.41
    POSITIVE LOGITS
    __*/
    0.92
     мәкал
    0.90
     Efq
    0.85
    ChildIndex
    0.85
     ExecuteAsync
    0.82
     bezeichneter
    0.81
    Identyfik
    0.81
    ImageContext
    0.81
    DockStyle
    0.80
    Portale
    0.79
    Activations Density 0.028%

    No Known Activations