© 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. 0-RES-MATRYOSHKA-DC
    7. 11292
    Prev
    Next
    INDEX
    Explanations

    the presence of detectable signals in specialized sensor data

    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
    EndInit
    -0.79
     unknownFields
    -0.77
    IonicModule
    -0.74
    Hentet
    -0.73
    /*
    -0.69
    enderror
    -0.66
    PreferredItem
    -0.65
    providedIn
    -0.65
    SocketAddress
    -0.65
    LOAT
    -0.64
    POSITIVE LOGITS
     detectable
    2.69
    tectable
    1.43
     perceptible
    0.94
     measurable
    0.94
     discernible
    0.87
     observable
    0.71
     detec
    0.71
     distinguishable
    0.69
     noticeable
    0.63
     unde
    0.63
    Activations Density 0.001%

    No Known Activations