© 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. 5-CLT-HP
    7. 1015
    Prev
    Next
    INDEX
    Explanations

    proximity

    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
    uh
    -0.47
    ard
    -0.46
    yu
    -0.44
     Dernière
    -0.44
    InstrumentedTest
    -0.43
    -
    -0.43
    ling
    -0.43
     surla
    -0.43
    发表于
    -0.43
    it
    -0.43
    POSITIVE LOGITS
     another
    0.86
     other
    0.82
     the
    0.79
    another
    0.71
     several
    0.68
    bootstrapcdn
    0.63
     a
    0.63
     to
    0.60
     two
    0.60
    อื่น
    0.60
    Activations Density 0.007%

    No Known Activations