© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2742
    Prev
    Next
    INDEX
    Explanations

    is

    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
     SwitchCompat
    -0.46
     voort
    -0.41
     удовольствием
    -0.40
     writing
    -0.39
     foto
    -0.39
    erdings
    -0.39
     있습니다
    -0.38
    foto
    -0.37
    İstinadlar
    -0.37
     (@
    -0.36
    POSITIVE LOGITS
    MigrationBuilder
    0.69
    #+#
    0.66
    XmlAccessType
    0.63
    XmlEnum
    0.63
    ClientSize
    0.61
     enough
    0.61
    pushFollow
    0.59
     jsPsych
    0.58
     JpaRepository
    0.57
     equivale
    0.57
    Activations Density 0.002%

    No Known Activations