© 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. 4405
    Prev
    Next
    INDEX
    Explanations

    metals/colors/scrap

    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
    CrossRef
    -0.56
    annan
    -0.55
    BeginContext
    -0.54
    TypedDataSet
    -0.53
     in
    -0.53
     significant
    -0.52
    ми
    -0.51
     too
    -0.51
     min
    -0.50
    synchronized
    -0.50
    POSITIVE LOGITS
    $_['
    0.63
     Houſe
    0.52
     épaules
    0.45
     متعلقه
    0.44
    meteor
    0.44
     Blo
    0.43
    htar
    0.40
     Ced
    0.40
     Aar
    0.40
    "';
    0.40
    Activations Density 0.017%

    No Known Activations