© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95365
    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
    -2.52
     Bit
    -1.54
     bits
    -1.53
    bit
    -1.38
    Bit
    -1.27
     BIT
    -1.27
     bitten
    -1.00
    BIT
    -0.94
     Bits
    -0.94
     oxygen
    -0.89
    POSITIVE LOGITS
    sp
    0.61
    ties
    0.59
    ty
    0.58
    st
    0.56
    cur
    0.56
    ted
    0.55
    str
    0.55
    no
    0.54
    ns
    0.50
    hes
    0.50
    Activations Density 0.595%

    No Known Activations