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. 9-RES-MATRYOSHKA-DC
    4. 16726
    Prev
    Next
    INDEX
    Explanations

    the word "Enter"

    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
    HasAnnotation
    -0.92
     saites
    -0.88
    BagConstraints
    -0.87
    
    -0.85
     JpaRepository
    -0.84
    nologue
    -0.82
    objc
    -0.80
    fucker
    -0.77
    Luffy
    -0.76
    ^(@)
    -0.75
    POSITIVE LOGITS
     /^
    0.64
     ط
    0.63
    amet
    0.60
    Pars
    0.60
    com
    0.59
    als
    0.57
    URN
    0.57
    m
    0.57
    UND
    0.56
     أم
    0.56
    Activations Density 0.005%

    No Known Activations