© 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. 7063
    Prev
    Next
    INDEX
    Explanations

    occurrences of event-related tokens, especially those labeled as 'ev'

    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
     FetchType
    -0.74
     صوتيه
    -0.72
    ugno
    -0.67
    quelize
    -0.66
    UwU
    -0.65
    tonsoft
    -0.64
    TWA
    -0.63
    CURLOPT
    -0.62
    audiovisuel
    -0.62
     Caw
    -0.61
    POSITIVE LOGITS
    ev
    3.17
     ev
    2.98
     Ev
    2.77
    Ev
    2.70
    EV
    2.17
     EV
    2.08
    evs
    1.53
     eviction
    1.42
     év
    1.30
    eva
    1.29
    Activations Density 0.028%

    No Known Activations