© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1910
    Prev
    Next
    INDEX
    Explanations

    the word "deep" along with some words that are conceptually the opposite of superficial

    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
     Roskov
    -0.91
     Normdatei
    -0.87
     insuffisamment
    -0.82
    
    -0.79
    Datuak
    -0.77
    makeatother
    -0.75
    rshire
    -0.75
    StreetMap
    -0.74
     referrerpolicy
    -0.73
    RegistryLite
    -0.73
    POSITIVE LOGITS
     deep
    3.56
     Deep
    3.27
    deep
    3.20
    Deep
    3.19
     DEEP
    3.09
    DEEP
    2.86
     deeper
    2.73
     deepest
    2.73
     depth
    2.53
     Deeper
    2.39
    Activations Density 0.187%

    No Known Activations