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. 22-CLT-HP
    4. 74445
    Prev
    Next
    INDEX
    Explanations

    Code licensing information

    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
     通販
    -0.63
    rrggbb
    -0.62
    +#+#
    -0.60
    GEBURTS
    -0.56
     saites
    -0.54
     "..\..\
    -0.53
    gonic
    -0.52
    SequentialGroup
    -0.52
    HasBeenSet
    -0.51
    arted
    -0.51
    POSITIVE LOGITS
    CardContent
    0.54
     vVar
    0.53
    AccessException
    0.52
    ature
    0.50
     onResponse
    0.49
    werde
    0.49
     Mende
    0.47
    iastes
    0.47
     Fray
    0.47
     anhydride
    0.46
    Activations Density 0.319%

    No Known Activations