© 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. 43984
    Prev
    Next
    INDEX
    Explanations

    ideas; reasoning

    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>
    -0.92
     success
    -0.50
     sense
    -0.49
     veci
    -0.43
    VERSION
    -0.43
     to
    -0.42
    version
    -0.42
     sources
    -0.40
    uarga
    -0.40
    versions
    -0.39
    POSITIVE LOGITS
     of
    0.93
    tagHelperRunner
    0.86
    ftagPool
    0.84
    AndEndTag
    0.82
    ngdoc
    0.79
    WebVitals
    0.75
    SharedDtor
    0.73
    __(/*!
    0.73
     CreateTagHelper
    0.72
     vuotta
    0.71
    Activations Density 0.056%

    No Known Activations