© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 5810
    Prev
    Next
    INDEX
    Explanations

    to be

    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
    ftagPool
    -0.62
    ,
    -0.59
     milioane
    -0.56
     pioggia
    -0.55
     كومونز
    -0.54
    تفصیلات
    -0.53
     pressione
    -0.51
     kérd
    -0.51
     thus
    -0.51
     piele
    -0.50
    POSITIVE LOGITS
    :");
    
    0.62
     سكانية
    0.57
    '});
    0.57
    '));
    0.55
    '));
    
    0.54
     preva
    0.54
    __(/*!
    0.54
    ')),
    0.53
    }]
    
    0.53
     himo
    0.52
    Activations Density 0.009%

    No Known Activations