© 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. 5-CLT-HP
    7. 91416
    Prev
    Next
    INDEX
    Explanations

    dates/time periods

    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
    wiście
    -0.44
     track
    -0.41
     Compli
    -0.40
     compliments
    -0.40
     Track
    -0.39
     srs
    -0.37
    entiment
    -0.37
     gemeint
    -0.36
    ערך
    -0.36
    }}
    -0.36
    POSITIVE LOGITS
     nakalista
    0.85
    saraba
    0.79
    脚注の使い方
    0.77
    mybatisplus
    0.76
     Italijanski
    0.74
     насељу
    0.73
     bezeichneter
    0.73
     تضيفلها
    0.73
    webElementGuid
    0.71
     nonatomic
    0.70
    Activations Density 0.003%

    No Known Activations