© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 707
    Prev
    Next
    INDEX
    Explanations

    Taxonomy

    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
    ceae
    -1.07
    iaceae
    -0.96
    optera
    -0.56
    opsida
    -0.54
    cidae
    -0.54
     EconPapers
    -0.54
    ney
    -0.48
    참고
    -0.46
    зулта
    -0.46
     EdgeInsets
    -0.45
    POSITIVE LOGITS
    \{\\
    0.74
     bones
    0.56
    fillable
    0.54
     newOwner
    0.54
    bedaan
    0.53
    Alguna
    0.53
    Zar
    0.52
     Banks
    0.52
     <>",
    0.52
     necro
    0.52
    Activations Density 0.032%

    No Known Activations