© 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. 6540
    Prev
    Next
    INDEX
    Explanations

    the beginning or initial point of a sequence or event

    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
    MessageTagHelper
    -0.89
    ValueGenerated
    -0.84
     HasFactory
    -0.77
     trajets
    -0.77
     صوتيه
    -0.77
     مرئيه
    -0.75
    contentLoaded
    -0.73
    ]")]
    -0.73
     HttpNotFound
    -0.72
    isContained
    -0.71
    POSITIVE LOGITS
     who
    0.63
    who
    0.62
    DOCTYPE
    0.51
     vies
    0.50
    To
    0.49
    PYX
    0.49
    Attributes
    0.48
    leştir
    0.48
    per
    0.47
    PER
    0.47
    Activations Density 0.749%

    No Known Activations