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. 20-CLT-HP
    4. 74057
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mergeFrom
    -0.57
     skr
    -0.49
     krop
    -0.43
     quelcon
    -0.43
    íts
    -0.42
    SourceChecksum
    -0.41
    ingue
    -0.40
    esprit
    -0.40
    ikation
    -0.39
    DataSetChanged
    -0.39
    POSITIVE LOGITS
     resourceCulture
    0.75
     OFDb
    0.59
    ########.
    0.59
    帖最后由
    0.57
     betweenstory
    0.56
    Rohy
    0.52
    енча
    0.51
    TEA
    0.51
    Hozzáférés
    0.50
     fallo
    0.50
    Activations Density 0.001%

    No Known Activations