© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97257
    Prev
    Next
    INDEX
    Explanations

    application or implementation

    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
     CreateTagHelper
    -0.75
    évaluateur
    -0.73
    homonymie
    -0.71
    enumi
    -0.71
    RefNanny
    -0.70
     viewType
    -0.67
    tagHelperRunner
    -0.65
    joba
    -0.65
     HttpStatusCode
    -0.64
    MIDDLEWARE
    -0.63
    POSITIVE LOGITS
     and
    0.54
    fully
    0.50
    SourceChecksum
    0.48
    ,
    0.40
    lessly
    0.40
     Gegenwart
    0.39
    мені
    0.38
    gjenge
    0.37
    newInstance
    0.37
     allemaal
    0.37
    Activations Density 0.008%

    No Known Activations