© 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. 2089
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
     jLabel
    -0.69
     CURIAM
    -0.57
    <bos>
    -0.54
     Paglinawan
    -0.52
     تضيفلها
    -0.52
    balleur
    -0.51
    ModelAdmin
    -0.50
    FundMe
    -0.50
    venidos
    -0.50
    WithMany
    -0.50
    POSITIVE LOGITS
    KommentareTeilen
    0.61
     للمعارف
    0.57
     incredible
    0.54
    XmlAccessorType
    0.53
     amazing
    0.50
     unbelievable
    0.50
     excellent
    0.50
     "..\..\
    0.47
     "..\..\..\
    0.47
    jątk
    0.47
    Activations Density 0.000%

    No Known Activations