© 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. 3474
    Prev
    Next
    INDEX
    Explanations

    wood

    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
    WriteBarrier
    -0.55
    iness
    -0.51
    ValueStyle
    -0.49
    awtextra
    -0.47
     Aldrich
    -0.47
    gore
    -0.46
    care
    -0.46
    shields
    -0.46
     Kalau
    -0.45
    cutting
    -0.45
    POSITIVE LOGITS
    ̈́
    0.60
    RegressionTest
    0.58
    rungsseite
    0.58
     Rank
    0.56
    ceuticals
    0.54
    jednoc
    0.52
     informasjon
    0.52
    exels
    0.51
    uisine
    0.51
     culturelles
    0.50
    Activations Density 0.002%

    No Known Activations