© 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. 45697
    Prev
    Next
    INDEX
    Explanations

    fecal

    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
     fecal
    -1.08
     feces
    -1.03
    ecal
    -0.76
     فريبيس
    -0.68
     cielos
    -0.60
    fec
    -0.58
    糞
    -0.55
     beginnetje
    -0.53
    opcao
    -0.53
    kezi
    -0.52
    POSITIVE LOGITS
    ed
    0.58
     betweenstory
    0.57
    ies
    0.56
    land
    0.55
    teen
    0.52
    id
    0.52
    age
    0.52
    eronau
    0.51
    es
    0.50
     matter
    0.50
    Activations Density 0.089%

    No Known Activations