© 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. 20-CLT-HP
    7. 72491
    Prev
    Next
    INDEX
    Explanations

    presenting evidence

    np_max-act-logits · 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
    dientemente
    -0.70
     stanovnika
    -0.69
    醐
    -0.63
    ToProps
    -0.62
    __);
    -0.59
    ագրություններ
    -0.59
    //});
    -0.58
    ніципа
    -0.56
     sánh
    -0.56
    ](#
    -0.55
    POSITIVE LOGITS
     Exhibit
    0.62
     proof
    0.56
     cause
    0.53
     grounds
    0.53
     Cause
    0.53
     Offisielt
    0.52
     little
    0.52
     notice
    0.52
     evidence
    0.51
     autorytatywna
    0.50
    Activations Density 0.001%

    No Known Activations