© 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. 39858
    Prev
    Next
    INDEX
    Explanations

    cemia

    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
     فريبيس
    -0.64
     fermés
    -0.63
    #+#
    -0.63
     normaux
    -0.63
    twimg
    -0.62
    ArrowToggle
    -0.61
     sólidos
    -0.61
     définiti
    -0.60
     lèvres
    -0.60
     därför
    -0.59
    POSITIVE LOGITS
     domain
    0.63
     mord
    0.60
    posedge
    0.58
    a
    0.58
    łku
    0.57
     domains
    0.56
    WaitGroup
    0.54
    o
    0.54
     wor
    0.53
    EndContext
    0.53
    Activations Density 1.560%

    No Known Activations