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. 31173
    Prev
    Next
    INDEX
    Explanations

    words that suggest a strong negative opinion

    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
     hal
    -0.57
    rapp
    -0.54
    aspectj
    -0.54
    leit
    -0.54
    agrad
    -0.52
     Gleaner
    -0.52
    quito
    -0.52
     JUSTICE
    -0.52
    מיש
    -0.52
     hesit
    -0.51
    POSITIVE LOGITS
     outright
    0.75
     mourut
    0.61
     manifiesta
    0.60
     ativos
    0.58
    PreferredItem
    0.56
    ſelf
    0.55
     étoit
    0.55
     ſtate
    0.55
    CppCodeGen
    0.54
     quæ
    0.54
    Activations Density 0.214%

    No Known Activations