© 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. 5362
    Prev
    Next
    INDEX
    Explanations

    2

    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
    ########.
    -0.85
     Италијани
    -0.63
    __*/
    -0.61
    webElement
    -0.58
     oprot
    -0.57
    GeneratedCode
    -0.56
    delwed
    -0.53
    IonicModule
    -0.53
    Demografie
    -0.52
    ⓧ
    -0.50
    POSITIVE LOGITS
    nd
    0.85
    ND
    0.71
    XmlAccessType
    0.70
    9
    0.69
     nd
    0.60
    DataAnnotations
    0.60
    WriteTagHelper
    0.60
    3
    0.58
    8
    0.56
    nds
    0.55
    Activations Density 0.001%

    No Known Activations