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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45077
    Prev
    Next
    INDEX
    Explanations

    scientific, uncommon words

    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
    bane
    -0.72
    Synonyms
    -0.67
    bun
    -0.55
    +#+#
    -0.55
     Struct
    -0.50
     pior
    -0.48
    iencias
    -0.47
    tür
    -0.47
     strerror
    -0.46
    ersburg
    -0.46
    POSITIVE LOGITS
    }))
    0.71
     MainAxisSize
    0.70
    mbic
    0.65
    TypedDataSet
    0.64
    LayoutPanel
    0.63
    WithIOException
    0.63
    ">//
    0.60
     Мексичка
    0.60
    getMenuInflater
    0.59
    adaptiveStyles
    0.58
    Activations Density 0.990%

    No Known Activations