© 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. 5-CLT-HP
    7. 96294
    Prev
    Next
    INDEX
    Explanations

    Code and Data

    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
     '\\;'
    -0.83
    InitVars
    -0.79
    出版年
    -0.78
    RenderAtEndOf
    -0.76
     TextInputType
    -0.74
     newBuilder
    -0.70
    _
    -0.69
    endphp
    -0.68
    PropertyChanging
    -0.68
     doubtnut
    -0.66
    POSITIVE LOGITS
     
    0.53
    <eos>
    0.47
    )(
    0.43
    GEBURTSDATUM
    0.42
    0
    0.41
    1
    0.41
    الحياه
    0.40
    Sub
    0.39
     ég
    0.35
    报
    0.35
    Activations Density 0.000%

    No Known Activations