© 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. 93384
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
    šin
    -0.47
     sguardo
    -0.45
    dawnictwo
    -0.45
     示例
    -0.43
     Gifts
    -0.43
    нейших
    -0.42
     gifts
    -0.42
     ließ
    -0.41
     saper
    -0.41
     regalos
    -0.40
    POSITIVE LOGITS
    abestanden
    0.88
    #+#
    0.80
     مرئيه
    0.72
    MigrationBuilder
    0.68
     ***!
    0.68
    styleType
    0.68
    SourceChecksum
    0.67
    lgari
    0.66
    AndroidJUnit
    0.65
    };*/
    0.64
    Activations Density 0.001%

    No Known Activations