© 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. 0-CLT-HP
    7. 94949
    Prev
    Next
    INDEX
    Explanations

    row

    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
     unlikely
    -0.74
    likely
    -0.69
     row
    -0.66
     likely
    -0.65
    unlikely
    -0.63
     prêt
    -0.52
    ruly
    -0.52
    ården
    -0.50
    IEVE
    -0.50
    IMAS
    -0.50
    POSITIVE LOGITS
    GEBURTSDATUM
    1.23
     ProtoMessage
    0.86
     AssemblyCulture
    0.81
    DeleteBehavior
    0.81
     Савезне
    0.77
    Personensuche
    0.75
     NUKAT
    0.74
     resourceCulture
    0.74
    MemoryWarning
    0.73
     dAtA
    0.73
    Activations Density 0.041%

    No Known Activations