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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45994
    Prev
    Next
    INDEX
    Explanations

    them

    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
     disponibilités
    -0.58
    Clik
    -0.51
    shot
    -0.47
    berdayakan
    -0.46
    means
    -0.46
     wußte
    -0.46
     itſelf
    -0.46
    Shot
    -0.45
    KNOW
    -0.45
    plays
    -0.44
    POSITIVE LOGITS
     appear
    0.79
     gain
    0.73
     accumulate
    0.67
    省市镇
    0.67
     gather
    0.67
     remain
    0.66
     develop
    0.65
     feel
    0.65
     look
    0.65
     evolve
    0.64
    Activations Density 0.009%

    No Known Activations