© 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. 5-CLT-HP
    7. 96907
    Prev
    Next
    INDEX
    Explanations

    location

    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
     estekak
    -0.56
     ComVisible
    -0.48
    sizeCache
    -0.47
     AssemblyCulture
    -0.45
     honnête
    -0.44
    ContentAsync
    -0.44
    достатки
    -0.44
     ویکی‌پدیا
    -0.43
    iestety
    -0.41
     فريبيس
    -0.40
    POSITIVE LOGITS
    ArgsConstructor
    0.76
    dataclass
    0.63
    `),
    0.58
     getRule
    0.55
     Trains
    0.54
    évaluateur
    0.54
     CGRectMake
    0.54
    )`
    0.54
     AppCompatTheme
    0.53
     Schuyler
    0.52
    Activations Density 0.017%

    No Known Activations