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. 8-RES-MATRYOSHKA-DC
    4. 31270
    Prev
    Next
    INDEX
    Explanations

    uses of the word "importantly" or superlatives

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
     كومونز
    -0.69
    Aye
    -0.66
     resourceCulture
    -0.65
     kaarangay
    -0.64
    principalTable
    -0.63
    TryParse
    -0.61
     Ceinture
    -0.60
    SourceChecksum
    -0.59
    bcrypt
    -0.59
    äsident
    -0.58
    POSITIVE LOGITS
     importantly
    0.74
    何より
    0.51
    arakhand
    0.50
     laude
    0.48
     afield
    0.46
    IBinder
    0.45
    Pol
    0.43
     contextLoads
    0.43
    UnusedPrivate
    0.42
    earnings
    0.42
    Activations Density 0.080%

    No Known Activations