© 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. 4429
    Prev
    Next
    INDEX
    Explanations

    of

    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
    rungsseite
    -0.68
    ClientSize
    -0.67
     igång
    -0.66
     delà
    -0.63
     alltså
    -0.63
     degré
    -0.60
     lunghezza
    -0.59
    tonode
    -0.59
     invitamos
    -0.59
    sizeCache
    -0.58
    POSITIVE LOGITS
    atouille
    0.50
    [](
    0.47
     each
    0.47
    TagHelper
    0.47
     key
    0.46
    azine
    0.46
    原始内容存档于
    0.46
    prefixer
    0.45
    啶
    0.44
     setw
    0.44
    Activations Density 0.009%

    No Known Activations