© 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. 5-CLT-HP
    7. 96118
    Prev
    Next
    INDEX
    Explanations

    Questions

    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
     CreateTagHelper
    -1.09
    StoryboardSegue
    -0.98
    ReusableCell
    -0.89
    errHandler
    -0.84
     prochains
    -0.82
     will
    -0.76
     nanti
    -0.75
    CodeAttribute
    -0.75
     ***!
    -0.73
    DockStyle
    -0.72
    POSITIVE LOGITS
    ագրություններ
    0.49
     Make
    0.44
    weile
    0.44
     category
    0.44
    mixin
    0.43
     sk
    0.42
     scorso
    0.41
     مقاط
    0.40
     mittlerweile
    0.40
     make
    0.40
    Activations Density 0.020%

    No Known Activations