© 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. 96254
    Prev
    Next
    INDEX
    Explanations

    the

    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
    zerű
    -0.75
    __":
    -0.62
    umą
    -0.59
     متعلقه
    -0.59
     transparentes
    -0.58
     témoins
    -0.58
     chré
    -0.57
     altrimenti
    -0.55
     gevo
    -0.55
     acciaio
    -0.55
    POSITIVE LOGITS
    protoimpl
    0.67
    enchymal
    0.44
    extAlignment
    0.43
     otomatig
    0.43
     defaultstate
    0.42
     nonatomic
    0.41
    sizeCache
    0.41
    AttributeSet
    0.40
     commune
    0.40
    javadoc
    0.40
    Activations Density 0.007%

    No Known Activations