© 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. 92150
    Prev
    Next
    INDEX
    Explanations

    to

    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
     noires
    -0.56
    Many
    -0.52
    enumi
    -0.52
    many
    -0.51
     aveug
    -0.50
     blancs
    -0.47
     igång
    -0.47
    色は
    -0.47
    اعمال
    -0.46
     respeito
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.68
    disambiguation
    0.66
     tartalomajánló
    0.63
    __*/
    0.60
    WriteBarrier
    0.59
     propOrder
    0.58
     beginnetje
    0.57
    webElementXpaths
    0.57
    Vendredi
    0.57
    +#+
    0.57
    Activations Density 0.002%

    No Known Activations