© 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. 4450
    Prev
    Next
    INDEX
    Explanations

    comparisons with "as"

    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
    AutoScale
    -0.58
     referenties
    -0.56
     onCancelled
    -0.55
    PropertyChanging
    -0.53
     ComVisible
    -0.51
    ellular
    -0.51
     оригіналу
    -0.49
    stateParams
    -0.49
    MigrationBuilder
    -0.49
     So
    -0.49
    POSITIVE LOGITS
    IntoConstraints
    0.59
    __':
    0.54
    XmlAccessorType
    0.54
     thither
    0.51
     Linz
    0.50
    kiat
    0.48
     twain
    0.47
    <bos>
    0.47
     تانيه
    0.47
     gâ
    0.46
    Activations Density 0.000%

    No Known Activations