© 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. 97555
    Prev
    Next
    INDEX
    Explanations

    legal or code documents

    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
    rungsseite
    -1.13
    AndEndTag
    -1.13
     Paglinawan
    -1.13
     estekak
    -1.06
    Datuak
    -1.05
     للاسماء
    -1.05
    MigrationBuilder
    -1.02
    GEBURTSDATUM
    -0.90
    таратура
    -0.90
    IsContent
    -0.90
    POSITIVE LOGITS
    ,
    0.49
    vans
    0.44
    led
    0.43
     der
    0.42
    de
    0.41
     de
    0.41
    <sub>
    0.41
     Air
    0.41
    ades
    0.41
    Wat
    0.41
    Activations Density 0.116%

    No Known Activations