© 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. 1012
    Prev
    Next
    INDEX
    Explanations

    and, colon

    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
    BeginContext
    -0.55
     Lead
    -0.54
     receiving
    -0.53
    Backing
    -0.52
     about
    -0.51
    transQ
    -0.51
     other
    -0.50
    Lead
    -0.50
     Has
    -0.49
    posting
    -0.49
    POSITIVE LOGITS
    endpush
    0.65
    GEBURTSDATUM
    0.59
     nakalista
    0.57
     figure
    0.56
    poptosis
    0.55
     NTIS
    0.55
    IGraphics
    0.54
    MENAFN
    0.54
    })*/
    0.54
    Geological
    0.53
    Activations Density 0.002%

    No Known Activations