© 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. 91371
    Prev
    Next
    INDEX
    Explanations

    time

    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
    mappedBy
    -0.49
    Personendaten
    -0.46
    <bos>
    -0.45
     مواليد
    -0.42
    rijk
    -0.42
     ред
    -0.41
    stdbool
    -0.41
    EnableWeb
    -0.40
    ⓘ
    -0.40
    CppMethod
    -0.39
    POSITIVE LOGITS
    MigrationBuilder
    0.79
    EndInit
    0.70
    StoryboardSegue
    0.67
    IntoConstraints
    0.67
     getopt
    0.65
    IBar
    0.63
    ArgsConstructor
    0.63
     locul
    0.62
     closures
    0.60
    Jîn
    0.60
    Activations Density 0.071%

    No Known Activations