© 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. 1-CLT-HP
    7. 375
    Prev
    Next
    INDEX
    Explanations

    Col

    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
     Col
    -1.01
    Jeografia
    -0.84
    Col
    -0.61
    EDEFAULT
    -0.58
    NameInMap
    -0.55
     åt
    -0.54
    ItemBackground
    -0.54
     col
    -0.54
     Exacts
    -0.53
    ecture
    -0.52
    POSITIVE LOGITS
    s
    0.59
    lapsed
    0.55
    enumi
    0.50
     vendus
    0.49
    some
    0.48
    __*/
    0.46
     convertView
    0.45
    indro
    0.44
     tslint
    0.44
    kl
    0.42
    Activations Density 0.207%

    No Known Activations