© 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. 4-CLT-HP
    7. 4323
    Prev
    Next
    INDEX
    Explanations

    visual media

    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
     shows
    -0.75
    shows
    -0.56
     pictures
    -0.55
     showing
    -0.54
     Gambar
    -0.54
    zeigt
    -0.53
     Shows
    -0.53
     visuals
    -0.52
     show
    -0.52
    DIPSETTING
    -0.51
    POSITIVE LOGITS
    parsedMessage
    0.79
     devenus
    0.68
     محفوظة
    0.67
     الحره
    0.66
     bezeichneter
    0.66
    HasAnnotation
    0.65
    \{\\
    0.63
    .
    0.63
     venait
    0.61
     rencontré
    0.60
    Activations Density 0.006%

    No Known Activations