© 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. 20-CLT-HP
    7. 77880
    Prev
    Next
    INDEX
    Explanations

    File paths and algorithms

    np_max-act-logits · 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
     ujednoznacz
    -0.53
    WebElementEntity
    -0.52
    sunter
    -0.51
     nltk
    -0.50
    Décès
    -0.47
     morire
    -0.46
    chaff
    -0.46
    KJ
    -0.46
    JdbcTemplate
    -0.45
    alar
    -0.45
    POSITIVE LOGITS
    ItemBackground
    0.72
    djangoproject
    0.60
    WriteBarrier
    0.57
    kháu
    0.56
    shadowOpacity
    0.55
    VersionUID
    0.55
    Хьажоргаш
    0.54
    AddTagHelper
    0.53
    ApiModelProperty
    0.51
    новниш
    0.49
    Activations Density 0.010%

    No Known Activations