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. 1551
    Prev
    Next
    INDEX
    Explanations

    words related to crimes, arrests, and imprisonment

    oai_token-act-pair · gemini-2.0-flash

    crime and imprisonment

    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
     виправивши
    -0.79
     utafitiHapana
    -0.78
     linkovi
    -0.66
    WebVitals
    -0.64
    InstanceState
    -0.59
     Theſe
    -0.59
    ruptcy
    -0.57
     calendriers
    -0.57
    nahm
    -0.57
     autorytatywna
    -0.57
    POSITIVE LOGITS
     vielä
    0.45
    genstein
    0.45
     diretta
    0.44
     portata
    0.44
    ftagPool
    0.42
    ⓧ
    0.42
    Readers
    0.41
    barui
    0.41
     sentidos
    0.41
     mauvaises
    0.40
    Activations Density 5.844%

    No Known Activations