© 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. 0-CLT-HP
    7. 97491
    Prev
    Next
    INDEX
    Explanations

    problems or origins

    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
     originate
    -0.93
     originates
    -0.87
     originating
    -0.86
     arisen
    -0.84
     originated
    -0.83
     arises
    -0.81
    IBOutlet
    -0.77
    IsContent
    -0.76
    IsMutable
    -0.76
     Spreading
    -0.75
    POSITIVE LOGITS
     pret
    0.56
    OrEmpty
    0.52
    ospor
    0.47
     minor
    0.46
     impression
    0.46
     personal
    0.46
     empty
    0.45
     cast
    0.45
     pre
    0.43
     force
    0.43
    Activations Density 0.041%

    No Known Activations