© 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. 4-CLT-HP
    7. 3338
    Prev
    Next
    INDEX
    Explanations

    you

    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
     clicked
    -0.69
     climbed
    -0.66
     demolished
    -0.66
    Booked
    -0.65
     burned
    -0.65
     booked
    -0.64
     chipped
    -0.63
    flipped
    -0.62
     knocked
    -0.62
     booted
    -0.62
    POSITIVE LOGITS
    Personendaten
    0.55
     שוליים
    0.52
     estekak
    0.48
    Viitteet
    0.44
    BagConstraints
    0.44
    position
    0.44
    綱
    0.44
    tola
    0.44
    </thead>
    0.43
     Reverso
    0.42
    Activations Density 0.002%

    No Known Activations