© 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. 1085
    Prev
    Next
    INDEX
    Explanations

    too

    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
     незавершена
    -0.49
     också
    -0.48
    تقاوى
    -0.47
    csak
    -0.47
    kona
    -0.46
     matière
    -0.45
     dernières
    -0.45
    PostInfinity
    -0.44
     vieilles
    -0.44
     diverses
    -0.43
    POSITIVE LOGITS
     esternos
    0.60
     BrowserModule
    0.60
     organisation
    0.58
     resettlement
    0.57
    UnknownFields
    0.55
    fillType
    0.55
    dollis
    0.54
    icef
    0.54
    Diweddarwch
    0.54
     organisers
    0.54
    Activations Density 0.001%

    No Known Activations