© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4270
    Prev
    Next
    INDEX
    Explanations

    Code imports

    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
    fpm
    -0.54
    ोर्ट
    -0.51
    CJK
    -0.46
     Arti
    -0.44
     Credit
    -0.44
     Bí
    -0.44
    ядок
    -0.43
    SQ
    -0.43
    NOST
    -0.43
    ισ
    -0.42
    POSITIVE LOGITS
    ContentAsync
    0.75
    ).__
    0.73
    ViewFeatures
    0.68
    __':
    0.66
    UserScript
    0.64
     EconPapers
    0.63
    })`
    0.63
    __":
    0.62
    DIPSETTING
    0.61
    WebVitals
    0.60
    Activations Density 0.004%

    No Known Activations