© 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. 0-CLT-HP
    7. 97754
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    PI
    -0.83
    cu
    -0.73
    KommentareTeilen
    -0.73
    ick
    -0.69
    omp
    -0.68
     intptr
    -0.68
     lenker
    -0.65
    Jäh
    -0.65
    nonatomic
    -0.64
    sis
    -0.58
    POSITIVE LOGITS
     ferien
    0.62
     klubben
    0.60
     myſelf
    0.57
     kysy
    0.54
     surname
    0.54
     jäsen
    0.54
     nisso
    0.53
     pageContext
    0.53
     campagna
    0.51
     ilmo
    0.51
    Activations Density 0.089%

    No Known Activations