© 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. 91055
    Prev
    Next
    INDEX
    Explanations

    discussions or parameters

    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
     talks
    -0.71
     parameters
    -0.60
     Talks
    -0.54
    talks
    -0.54
     الحره
    -0.54
    aggio
    -0.51
     pens
    -0.48
    vola
    -0.47
    iah
    -0.47
     vo
    -0.46
    POSITIVE LOGITS
     myſelf
    0.87
     Cæsar
    0.82
     ſtate
    0.80
     themſelves
    0.79
     ſhe
    0.76
     whoſe
    0.75
     ſeveral
    0.74
     Jefus
    0.73
     uſed
    0.73
     becauſe
    0.72
    Activations Density 0.156%

    No Known Activations