Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74384
    Prev
    Next
    INDEX
    Explanations

    two

    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
    addCriterion
    -0.72
     كومونز
    -0.65
    PrototypeOf
    -0.59
     الاطلاع
    -0.59
     propOrder
    -0.58
     times
    -0.58
    MLLoader
    -0.57
    Personendaten
    -0.56
    ässig
    -0.55
    下载附件
    -0.53
    POSITIVE LOGITS
    føre
    0.53
    näm
    0.53
     kautta
    0.50
    TestTools
    0.49
    Gön
    0.49
    cow
    0.49
     samfun
    0.46
    pertoire
    0.46
     zů
    0.45
     yrity
    0.45
    Activations Density 0.007%

    No Known Activations