© 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. 96252
    Prev
    Next
    INDEX
    Explanations

    from

    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
    \{\\
    -0.67
     pleaſure
    -0.64
     виправивши
    -0.63
     ſmall
    -0.62
     ſtate
    -0.61
     reaſon
    -0.60
     deſt
    -0.60
     Grunde
    -0.60
     houſe
    -0.60
     tartalomajánló
    -0.59
    POSITIVE LOGITS
    webElementXpaths
    0.59
    ⓧ
    0.54
    NameInMap
    0.51
    ondissement
    0.50
    exels
    0.49
    instead
    0.49
    jspx
    0.47
     instead
    0.46
    errHandler
    0.46
    stet
    0.46
    Activations Density 0.007%

    No Known Activations