© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 844
    Prev
    Next
    INDEX
    Explanations

    conduct

    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
     skrift
    -0.66
     autorytatywna
    -0.61
    enderror
    -0.59
    UTERS
    -0.56
     stagione
    -0.52
     télécommande
    -0.52
    Cyfeiriadau
    -0.52
     Szen
    -0.51
     skolen
    -0.51
    TestingModule
    -0.50
    POSITIVE LOGITS
    JsonProperty
    0.59
    Varint
    0.56
    eará
    0.54
    siger
    0.54
     acquittal
    0.52
     Geraadpleegd
    0.51
    RuleContext
    0.51
    fillable
    0.50
     annex
    0.49
     melts
    0.49
    Activations Density 0.048%

    No Known Activations