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. 1614
    Prev
    Next
    INDEX
    Explanations

    terms related to natural resources and family

    oai_token-act-pair · gemini-2.0-flash

    natural

    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
    <?
    -0.65
     IBOutlet
    -0.56
    contentLoaded
    -0.56
    StatusOK
    -0.56
    ::_('
    -0.55
    IBOutlet
    -0.53
    LookAnd
    -0.53
     RSI
    -0.50
    ామ
    -0.50
     cô
    -0.50
    POSITIVE LOGITS
     NSCoder
    0.56
    __))
    0.55
     tartalomajánló
    0.54
    elemField
    0.53
     tropic
    0.50
    itope
    0.50
    ospel
    0.49
    ionine
    0.49
     kasarigan
    0.49
     isotopes
    0.48
    Activations Density 6.078%

    No Known Activations