© 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. 4442
    Prev
    Next
    INDEX
    Explanations

    as

    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
     HasFactory
    -0.63
     professionnels
    -0.61
     eût
    -0.61
    twimg
    -0.60
     esempio
    -0.59
     Efq
    -0.57
     esimerkiksi
    -0.56
     témo
    -0.56
     segü
    -0.56
     réunis
    -0.55
    POSITIVE LOGITS
    SequentialGroup
    0.59
    httphttps
    0.56
     appropriate
    0.54
     œ
    0.50
    AddTagHelper
    0.50
    poque
    0.49
    SuppressMessage
    0.48
     subs
    0.47
    CodedInputStream
    0.46
    iastes
    0.46
    Activations Density 0.001%

    No Known Activations