© 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. 1-CLT-HP
    7. 12233
    Prev
    Next
    INDEX
    Explanations

    math expressions

    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
     kasarigan
    -0.89
     féminine
    -0.88
     Réponses
    -0.85
     stället
    -0.82
     pédagogique
    -0.81
     Roskov
    -0.81
     imprimée
    -0.80
    دانشنامهٔ
    -0.80
     calendriers
    -0.80
     AssemblyVersion
    -0.79
    POSITIVE LOGITS
    -
    0.49
    <strong>
    0.47
    delta
    0.47
    sqrt
    0.47
    dev
    0.45
    *
    0.44
    <b>
    0.44
    pi
    0.44
    mu
    0.44
    sum
    0.43
    Activations Density 1.002%

    No Known Activations