© 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. 91688
    Prev
    Next
    INDEX
    Explanations

    began

    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
     الحره
    -0.62
     виправивши
    -0.59
    NameInMap
    -0.57
    rungsseite
    -0.54
    MigrationBuilder
    -0.49
    AndEndTag
    -0.47
    UserScript
    -0.45
    she
    -0.44
    msgTypes
    -0.44
    umab
    -0.42
    POSITIVE LOGITS
    Sklici
    0.71
     Baillargeon
    0.62
     мәкал
    0.60
     some
    0.59
    Jegyzetek
    0.57
    GroupLayout
    0.57
    )++;
    0.57
    closedir
    0.57
    ampire
    0.56
     Désolé
    0.55
    Activations Density 0.000%

    No Known Activations