© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12235
    Prev
    Next
    INDEX
    Explanations

    code examples

    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
    utnant
    -0.58
     imageNamed
    -0.55
    orsese
    -0.51
    iteness
    -0.50
     otomatig
    -0.50
    ontin
    -0.49
    defn
    -0.49
    assination
    -0.49
    sonian
    -0.48
    yarnpkg
    -0.48
    POSITIVE LOGITS
    رشف
    0.63
    EndContext
    0.59
    olfen
    0.55
    لينكات
    0.51
     skipping
    0.48
     Crunch
    0.48
     Squeeze
    0.48
     Matcha
    0.48
     Nuts
    0.47
     umbrellas
    0.47
    Activations Density 0.022%

    No Known Activations