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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16170
    Prev
    Next
    INDEX
    Explanations

    information related to film production, distribution and the people involved

    oai_token-act-pair · gemini-2.0-flash

    java code

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     consistency
    -0.45
    AnchorStyles
    -0.44
     appreciated
    -0.43
     household
    -0.42
    oft
    -0.42
    ем
    -0.41
    ciliation
    -0.41
    Ignoring
    -0.40
     reasonable
    -0.40
    INOS
    -0.40
    POSITIVE LOGITS
    onAttach
    0.82
    Personensuche
    0.77
    новништво
    0.69
    tvguidetime
    0.68
     AttributeSet
    0.64
     lenker
    0.64
    contentLoaded
    0.61
     CreateTagHelper
    0.61
    VersionUID
    0.60
     Xunit
    0.58
    Activations Density 1.416%

    No Known Activations