© 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. 438
    Prev
    Next
    INDEX
    Explanations

    Cs

    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
    es
    -0.54
     архивлан
    -0.54
     intptr
    -0.52
    isar
    -0.49
    ruary
    -0.47
    Numerology
    -0.46
     الحره
    -0.46
    locations
    -0.46
    seit
    -0.45
     سرا
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.76
    IVEREF
    0.69
    IsContent
    0.63
    ptonshire
    0.54
     ioutil
    0.53
    Personendaten
    0.52
    gdx
    0.52
    ioutil
    0.52
    UGAL
    0.51
     Planta
    0.51
    Activations Density 0.022%

    No Known Activations