© 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. 1-CLT-HP
    7. 14917
    Prev
    Next
    INDEX
    Explanations

    early

    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
    Facades
    -0.75
    enterOuterAlt
    -0.73
    WriteLiteral
    -0.70
     early
    -0.66
    enumii
    -0.65
    ########.
    -0.65
    early
    -0.63
    databind
    -0.63
    κτηρισ
    -0.62
    Portály
    -0.60
    POSITIVE LOGITS
     morning
    0.51
     evening
    0.51
     mornings
    0.50
     evenings
    0.49
     MORNING
    0.47
     bedtime
    0.46
    morning
    0.45
     Tomorrow
    0.45
    __":
    0.45
     Tuesday
    0.43
    Activations Density 0.011%

    No Known Activations