© 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. 92084
    Prev
    Next
    INDEX
    Explanations

    login

    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
    LayoutStyle
    -0.59
    VIAF
    -0.55
     VIAF
    -0.55
     pinulongan
    -0.54
     مشين
    -0.54
     ModelExpression
    -0.54
     незавершена
    -0.53
     Walkover
    -0.53
    原始内容存档于
    -0.52
     <<<<<<<<<<<<<<
    -0.52
    POSITIVE LOGITS
    FormTagHelper
    0.69
    FormsModule
    0.59
    enumi
    0.55
     ExecuteAsync
    0.54
    AutoField
    0.53
    mund
    0.48
    asis
    0.47
     required
    0.46
    eeded
    0.46
    solids
    0.46
    Activations Density 0.009%

    No Known Activations