© 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. 91970
    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
    -2.17
    bit
    -2.13
    Bit
    -1.80
     Bit
    -1.80
    BIT
    -1.68
     BIT
    -1.40
    bite
    -0.95
    i
    -0.94
    ビット
    -0.89
    biter
    -0.88
    POSITIVE LOGITS
     Efq
    1.16
     Theſe
    1.16
     myſelf
    1.15
     itſelf
    1.10
     Shakspeare
    1.10
     Jefus
    1.05
     Monfieur
    1.02
     himſelf
    1.02
     themſelves
    1.02
     Reſ
    1.01
    Activations Density 0.613%

    No Known Activations