© 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. 405
    Prev
    Next
    INDEX
    Explanations

    Building/construction

    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
    krishnan
    -0.55
    styleUrls
    -0.45
     utilizarse
    -0.44
    jątk
    -0.42
    zob
    -0.40
    complexType
    -0.40
     surla
    -0.40
     isSet
    -0.40
    Stayed
    -0.39
    yelidikan
    -0.39
    POSITIVE LOGITS
     bershka
    0.68
     Viter
    0.65
    IContainer
    0.63
    ########.
    0.62
    τια
    0.57
    ImageContext
    0.57
    }),
    0.57
    ParallelGroup
    0.57
    HandleFunc
    0.56
     Hannibal
    0.55
    Activations Density 0.012%

    No Known Activations