© 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. 97644
    Prev
    Next
    INDEX
    Explanations

    ow

    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
    ow
    -0.78
    aged
    -0.64
    owa
    -0.60
    a
    -0.54
    oid
    -0.48
    adine
    -0.43
     chiara
    -0.42
     personali
    -0.41
     solares
    -0.40
     irány
    -0.39
    POSITIVE LOGITS
     pinulongan
    1.02
     Majefty
    1.00
    ValueStyle
    0.98
     HasFactory
    0.93
     becauſe
    0.91
     snippetHide
    0.91
     themſelves
    0.91
    ⓧ
    0.91
     myſelf
    0.90
    Referencies
    0.88
    Activations Density 1.616%

    No Known Activations