© 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. 5-CLT-HP
    7. 92793
    Prev
    Next
    INDEX
    Explanations

    archives and documents

    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
    parsedMessage
    -0.64
    XmlAccessType
    -0.63
    WithMany
    -0.63
     JpaRepository
    -0.59
     jsPsych
    -0.59
    setBold
    -0.56
     ModelRenderer
    -0.56
    __(/*!
    -0.55
    riga
    -0.54
    ear
    -0.54
    POSITIVE LOGITS
    mybatisplus
    0.58
    fseek
    0.49
    原始内容存档
    0.49
     rese
    0.42
    NUMX
    0.41
     neutral
    0.41
    ьаж
    0.40
    SBATCH
    0.40
     typename
    0.40
    ябре
    0.40
    Activations Density 0.008%

    No Known Activations