© 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. 2160
    Prev
    Next
    INDEX
    Explanations

    of

    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
    AutoField
    -0.58
    ########.
    -0.55
     leaft
    -0.53
     Diſ
    -0.52
    GOTREF
    -0.52
     leaſt
    -0.51
    Obrázky
    -0.50
    IActionResult
    -0.50
     <=",
    -0.50
     ſeveral
    -0.49
    POSITIVE LOGITS
     desperation
    0.65
     ignorance
    0.65
     being
    0.60
     geography
    0.60
    IsContent
    0.59
     greed
    0.58
     arrogance
    0.57
     luck
    0.57
    InSection
    0.56
    abond
    0.56
    Activations Density 0.001%

    No Known Activations