© 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. 77191
    Prev
    Next
    INDEX
    Explanations

    Music albums and songs

    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
     وتسجيلات
    -0.69
     judiciaire
    -0.63
    EndInit
    -0.60
    äsident
    -0.58
     DPM
    -0.54
     Dora
    -0.54
    Dora
    -0.54
     SSR
    -0.53
    יע
    -0.53
     squire
    -0.53
    POSITIVE LOGITS
     nahilalakip
    0.66
    Kariera
    0.53
    RotationOrder
    0.50
     recevrez
    0.48
     hard
    0.48
     PeEnEo
    0.47
    CppCodeGen
    0.47
     rock
    0.46
    protoimpl
    0.45
    complexContent
    0.44
    Activations Density 0.003%

    No Known Activations