Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1673
    Prev
    Next
    INDEX
    Explanations

    words related to violence and terrorism

    oai_token-act-pair · gemini-2.0-flash

    terrorism and related concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.76
     mxArray
    -0.75
    rrggbb
    -0.74
     NSCoder
    -0.70
     lenker
    -0.68
    ValueStyle
    -0.67
    GOTREF
    -0.66
    MigrationBuilder
    -0.64
     transfieras
    -0.64
    clientY
    -0.60
    POSITIVE LOGITS
     TA
    0.43
     ويكيميديا
    0.42
    atorium
    0.42
    ount
    0.41
     pavillon
    0.41
    ktop
    0.41
    inander
    0.40
     Gama
    0.40
    TagMode
    0.40
     weh
    0.40
    Activations Density 7.530%

    No Known Activations