© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74681
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · 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
    "}")
    -0.57
    Попис
    -0.56
    HRT
    -0.54
    ༘
    -0.54
    engo
    -0.54
    Numerade
    -0.54
    TimerTask
    -0.54
    sique
    -0.53
     Ott
    -0.52
    OVID
    -0.51
    POSITIVE LOGITS
     تضيفلها
    0.63
     lenker
    0.56
     confronti
    0.53
     незавершена
    0.52
     présence
    0.51
     Paglinawan
    0.51
     movimenti
    0.50
     صوتيه
    0.49
    law
    0.47
     ujednoznacz
    0.47
    Activations Density 0.004%

    No Known Activations