© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5253
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "beam" with high intensity

    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
    новниш
    -0.76
     itſelf
    -0.72
     Référence
    -0.71
    bootstrapcdn
    -0.71
     myſelf
    -0.71
    HasAnnotation
    -0.69
    VITA
    -0.68
     "..\..\..\
    -0.68
     Acon
    -0.68
    HandlerContext
    -0.67
    POSITIVE LOGITS
     beam
    2.95
    beam
    2.58
     Beam
    2.48
     beams
    2.45
    Beam
    2.41
    beams
    2.13
     Beams
    2.00
     BEAM
    1.96
    BEAM
    1.77
     beamed
    1.50
    Activations Density 0.010%

    No Known Activations