© 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. 0-CLT-HP
    7. 42271
    Prev
    Next
    INDEX
    Explanations

    }

    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
    odal
    -2.14
    脚注の使い方
    -0.51
    HomeAsUpEnabled
    -0.48
    mybatisplus
    -0.44
    sbericht
    -0.44
    AndEndTag
    -0.44
    таратура
    -0.43
    wpi
    -0.42
     touch
    -0.41
    Past
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.68
    Jereo
    0.67
    asonic
    0.65
    entibus
    0.65
    ewski
    0.63
    𓃵
    0.62
    Vezi
    0.61
    ikyuu
    0.61
    zzleHttp
    0.61
    جغرافيا
    0.60
    Activations Density 0.402%

    No Known Activations