© 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. 5-CLT-HP
    7. 2201
    Prev
    Next
    INDEX
    Explanations

    and

    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
    tvguidetime
    -0.65
     élus
    -0.63
     témoins
    -0.60
     traités
    -0.60
     réguli
    -0.59
     graphiques
    -0.58
     particuliers
    -0.57
     escuchado
    -0.56
     vantaggi
    -0.55
     mères
    -0.55
    POSITIVE LOGITS
     these
    0.64
     reflexes
    0.53
     circuits
    0.52
     Audiodateien
    0.52
     domains
    0.51
     wheels
    0.50
     gears
    0.50
     parameters
    0.50
     sugars
    0.49
    
    0.49
    Activations Density 0.002%

    No Known Activations