© 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. 20-CLT-HP
    7. 77459
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · 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
    tvguidetime
    -0.63
     TAKE
    -0.60
    KURZBESCHREIBUNG
    -0.60
     take
    -0.60
    Take
    -0.59
     Take
    -0.59
    arakhand
    -0.59
    TAKE
    -0.59
    take
    -0.59
    AddWithValue
    -0.58
    POSITIVE LOGITS
    :+:
    0.52
     resourceCulture
    0.51
    .*")]
    0.49
    Begriffsklä
    0.47
     personal
    0.44
    personal
    0.44
     consultato
    0.43
     vôtre
    0.42
     voluntary
    0.42
    Personal
    0.42
    Activations Density 0.000%

    No Known Activations