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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11086
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific and medical research methods, including imaging, analysis, genes, mutations, and studies.

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb 'allow'

    np_token-act-pair-logits · gpt-4o-mini

    allow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    AndEndTag
    -0.78
    XmlAccessType
    -0.64
     htons
    -0.61
    </thead>
    -0.60
     Walkover
    -0.60
    Välislingid
    -0.59
     Italijanski
    -0.59
    
    -0.58
     preventiva
    -0.58
     виправивши
    -0.57
    POSITIVE LOGITS
     allow
    2.77
     allowing
    2.61
     Allow
    2.52
     allowed
    2.50
    Allow
    2.48
     allows
    2.48
    allow
    2.36
     Allowing
    2.36
     ALLOW
    2.25
    allowing
    2.19
    Activations Density 7.104%

    No Known Activations