© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 337
    Prev
    Next
    INDEX
    Explanations

    support, funding, licensing

    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
    にあります
    -0.42
    스템
    -0.41
    grown
    -0.41
     raíces
    -0.40
     llegó
    -0.40
    にある
    -0.40
    mian
    -0.39
    alini
    -0.39
    mbo
    -0.39
    zeigt
    -0.39
    POSITIVE LOGITS
     '\\;'
    0.91
    CppMethod
    0.82
     by
    0.80
    Бахар
    0.74
    Obrázky
    0.70
     ModelExpression
    0.70
    endphp
    0.68
    EndInit
    0.67
     للمعارف
    0.65
     مرئيه
    0.65
    Activations Density 0.039%

    No Known Activations