Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11296
    Prev
    Next
    INDEX
    Explanations

    bit

    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
     Bit
    -0.93
     bit
    -0.92
     BIT
    -0.85
    Bit
    -0.82
     Bits
    -0.76
     bitten
    -0.71
    BIT
    -0.70
     bits
    -0.69
    tagHelperRunner
    -0.66
    bit
    -0.64
    POSITIVE LOGITS
    validator
    0.51
    flag
    0.49
    bra
    0.49
    fight
    0.48
    field
    0.48
    Bra
    0.47
     oreille
    0.47
     Federation
    0.46
    baka
    0.45
    Brave
    0.44
    Activations Density 0.013%

    No Known Activations