© 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. 45285
    Prev
    Next
    INDEX
    Explanations

    heter

    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
     Audiodateien
    -0.80
     Carbon
    -0.79
     carbon
    -0.77
     prisonniers
    -0.72
     carbone
    -0.71
    Carbon
    -0.69
    primary
    -0.67
     carbono
    -0.66
    tanleria
    -0.64
     חיצוניים
    -0.63
    POSITIVE LOGITS
    izing
    0.59
     ring
    0.53
    spire
    0.53
     dioxide
    0.52
    ized
    0.50
    MLLoader
    0.49
     nuisance
    0.48
    ISTIC
    0.47
    istische
    0.46
    ']))
    0.46
    Activations Density 0.175%

    No Known Activations