© 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. 4-CLT-HP
    7. 3373
    Prev
    Next
    INDEX
    Explanations

    Technical/random text

    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
     wikipagina
    -0.66
     varandra
    -0.56
     sanitaires
    -0.56
     réguli
    -0.53
     chré
    -0.52
     religieuses
    -0.52
    expandindo
    -0.51
     initComponents
    -0.51
     emprunt
    -0.50
     étoit
    -0.49
    POSITIVE LOGITS
    shund
    0.63
    >>;
    0.62
    unif
    0.61
    prefixer
    0.61
    6
    0.58
     fluency
    0.55
     recital
    0.55
    5
    0.55
    SPJ
    0.54
     LUT
    0.53
    Activations Density 0.000%

    No Known Activations