© 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. 38843
    Prev
    Next
    INDEX
    Explanations

    quality ranking

    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
    èdia
    -0.72
     CreateTagHelper
    -0.71
     GRADE
    -0.68
    Grades
    -0.67
    grades
    -0.66
    ichord
    -0.65
     BrowserModule
    -0.64
     pinulongan
    -0.64
     defStyle
    -0.63
    otheby
    -0.63
    POSITIVE LOGITS
    <bos>
    0.71
    esModule
    0.55
    rawDesc
    0.53
    Expose
    0.47
    Хьажоргаш
    0.45
    occupe
    0.45
    šanās
    0.44
     voodoo
    0.43
     spacy
    0.42
     chance
    0.41
    Activations Density 0.146%

    No Known Activations