© 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. 4-CLT-HP
    7. 3518
    Prev
    Next
    INDEX
    Explanations

    unab

    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
     صوتيه
    -0.64
    Демографія
    -0.59
    setVerticalGroup
    -0.58
     дописавши
    -0.56
     gynhyrchwyd
    -0.55
     consultato
    -0.54
    écriture
    -0.49
     continúas
    -0.49
    IVEREF
    -0.49
    userDao
    -0.48
    POSITIVE LOGITS
     PropTypes
    0.49
    GraphicsUnit
    0.48
     Roskov
    0.48
    RenderAtEndOf
    0.47
    سمبر
    0.46
    StartTag
    0.46
     jätte
    0.45
    HostException
    0.45
    blooming
    0.45
    RTRS
    0.45
    Activations Density 0.002%

    No Known Activations