© 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. 22-RES-MATRYOSHKA-DC
    7. 1983
    Prev
    Next
    INDEX
    Explanations

    the word "real" or words containing "real-"

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الاطلاع
    -0.68
    rsiniz
    -0.67
    Scénario
    -0.64
    TabIndex
    -0.64
    tonode
    -0.60
    #+#
    -0.59
    eraard
    -0.57
    Skocz
    -0.56
    المناصب
    -0.55
    picos
    -0.54
    POSITIVE LOGITS
     estate
    1.23
    estate
    1.01
     Estate
    0.98
    ignment
    0.86
     REAL
    0.85
    REAL
    0.84
     ESTATE
    0.82
    Estate
    0.82
    Real
    0.81
     real
    0.78
    Activations Density 0.331%

    No Known Activations