© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 1220
    Prev
    Next
    INDEX
    Explanations

    the word "real", especially when followed by "time"

    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
    sätzlich
    -0.88
    principalTable
    -0.82
    transQ
    -0.76
    ividual
    -0.73
     Cushing
    -0.73
    StoryboardSegue
    -0.70
     kaynağından
    -0.69
    oporosis
    -0.68
    karz
    -0.68
    OGND
    -0.68
    POSITIVE LOGITS
     real
    1.69
    Real
    1.68
    real
    1.63
     Real
    1.63
    REAL
    1.54
     REAL
    1.46
    getReal
    1.07
     unreal
    0.97
     realtime
    0.91
    リアル
    0.89
    Activations Density 0.111%

    No Known Activations