© 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. 4-CLT-HP
    7. 4824
    Prev
    Next
    INDEX
    Explanations

    to/of

    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
    ThroughAttribute
    -0.78
    новниш
    -0.70
    enumii
    -0.69
    ंदीखरीदारी
    -0.69
     disponibilités
    -0.66
     consultato
    -0.65
     pageContext
    -0.62
    enumi
    -0.61
     nahilalakip
    -0.61
    <bos>
    -0.60
    POSITIVE LOGITS
     gehö
    0.46
     loopt
    0.45
     defStyle
    0.44
     actionBar
    0.43
     Complete
    0.43
    DeleteMapping
    0.42
    Completely
    0.42
    tagHelperRunner
    0.42
    цю
    0.42
     Completely
    0.41
    Activations Density 0.014%

    No Known Activations