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. 5862
    Prev
    Next
    INDEX
    Explanations

    words starting with the letters "und"

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "und"

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

    Und/Uns

    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
     CreateTagHelper
    -0.54
    Geplaatst
    -0.54
    EndGlobalSection
    -0.50
     AppCompatTheme
    -0.50
     SEDS
    -0.49
     Appeal
    -0.45
    migrationBuilder
    -0.44
    림
    -0.44
    ="@+
    -0.43
    ates
    -0.43
    POSITIVE LOGITS
     Paglinawan
    0.68
     متعلقه
    0.66
    })*/
    0.65
    >`;
    0.64
    basicConfig
    0.61
     <=",
    0.59
    SerializedName
    0.59
    FieldBuilder
    0.57
    \{\\
    0.55
    gerald
    0.55
    Activations Density 0.568%

    No Known Activations