© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14110
    Prev
    Next
    INDEX
    Explanations

    moving

    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
     nakalista
    -0.86
    GOTREF
    -0.81
     Shifting
    -0.75
    ReusableCell
    -0.72
     shifting
    -0.69
    mybatisplus
    -0.69
    UnitTesting
    -0.69
    enumii
    -0.69
    shifting
    -0.68
     kasarigan
    -0.66
    POSITIVE LOGITS
     last
    0.48
    verständlich
    0.44
     with
    0.42
     chi̍t
    0.42
     system
    0.41
     faster
    0.41
    dia
    0.41
    imen
    0.41
     fast
    0.41
     at
    0.40
    Activations Density 0.013%

    No Known Activations