© 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. 4791
    Prev
    Next
    INDEX
    Explanations

    job

    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
    󠁢
    -0.57
     pinulongan
    -0.57
     restTemplate
    -0.55
     leçon
    -0.55
    tvguidetime
    -0.54
    dė
    -0.54
    poons
    -0.53
     محفوظة
    -0.52
    andescent
    -0.52
    󠁿
    -0.52
    POSITIVE LOGITS
     description
    0.77
     specification
    0.69
     security
    0.65
    Specification
    0.59
     specifications
    0.59
     specs
    0.57
    description
    0.57
     utafitiHapana
    0.57
     Specification
    0.57
     satisfaction
    0.56
    Activations Density 0.001%

    No Known Activations