© 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. 0-CLT-HP
    7. 45187
    Prev
    Next
    INDEX
    Explanations

    base

    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
     {:.
    -0.59
    tagext
    -0.56
     exchange
    -0.56
    يانة
    -0.55
     Exchange
    -0.54
     disambiguazione
    -0.53
     thi
    -0.53
     bases
    -0.52
    TagMode
    -0.52
    存于互联网档案馆
    -0.51
    POSITIVE LOGITS
     Hinduism
    0.59
    NameInMap
    0.55
    idavit
    0.54
    AdapterFactory
    0.54
    tagHelperRunner
    0.54
    Rüyada
    0.50
    GeneratedCode
    0.50
    raeli
    0.50
     Manchuria
    0.49
    Rast
    0.48
    Activations Density 0.021%

    No Known Activations