© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5988
    Prev
    Next
    INDEX
    Explanations

    currency

    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
    ⓧ
    -0.59
    <bos>
    -0.56
    الإنجليزية
    -0.49
    tempat
    -0.45
     cref
    -0.44
    strokeStyle
    -0.44
    photobucket
    -0.44
    országban
    -0.44
     لينك
    -0.43
    وئ
    -0.43
    POSITIVE LOGITS
    runApp
    0.63
    ThroughAttribute
    0.59
    protoimpl
    0.55
    undred
    0.53
    RegistryLite
    0.52
     &___
    0.52
    aktery
    0.52
    ypep
    0.51
    OpenHelper
    0.51
     milj
    0.49
    Activations Density 0.005%

    No Known Activations