© 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. 96241
    Prev
    Next
    INDEX
    Explanations

    Immediately

    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
     About
    -0.44
     été
    -0.44
    र्भ
    -0.44
     ddelweddau
    -0.44
     løpet
    -0.43
     ViewGroup
    -0.43
    ValueStyle
    -0.41
    zelf
    -0.41
    χρι
    -0.41
    About
    -0.40
    POSITIVE LOGITS
    bootstrapcdn
    0.74
     you
    0.74
    出版年
    0.66
    السكان
    0.66
     we
    0.65
     there
    0.63
     I
    0.62
    MENAFN
    0.62
    WithMany
    0.61
     everyone
    0.59
    Activations Density 0.007%

    No Known Activations