© 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. 2-RES-MATRYOSHKA-DC
    7. 3193
    Prev
    Next
    INDEX
    Explanations

    references to scalar values or scalar quantities

    oai_token-act-pair · gpt-4.1-nano
    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
    riage
    -0.71
     مؤرشف
    -0.64
    లాలు
    -0.59
    BufferException
    -0.59
    expandindo
    -0.57
     hã
    -0.57
    ப்பட்டது
    -0.57
    #}
    -0.54
    __*/
    -0.54
    entista
    -0.54
    POSITIVE LOGITS
     scalar
    3.00
    scalar
    2.42
     Scalar
    2.34
     scalars
    2.30
    Scalar
    1.95
     Scalars
    1.35
    calar
    1.27
    Scalars
    1.05
     scaler
    1.05
    SCAL
    0.91
    Activations Density 0.002%

    No Known Activations