© 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. 0-CLT-HP
    4. 1199
    Prev
    Next
    INDEX
    Explanations

    emerging/new

    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
     препратки
    -0.73
    tagHelperRunner
    -0.69
     étoient
    -0.65
     magasiner
    -0.64
     onPostExecute
    -0.63
    ंदीखरीदारी
    -0.63
     tiennent
    -0.63
     avoient
    -0.62
     ferons
    -0.62
     ainfi
    -0.61
    POSITIVE LOGITS
    ly
    0.68
     B
    0.56
    ors
    0.56
    ios
    0.54
     Sch
    0.54
    ivre
    0.52
    ir
    0.52
     G
    0.52
     T
    0.51
    ity
    0.51
    Activations Density 0.067%

    No Known Activations