© 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. 3146
    Prev
    Next
    INDEX
    Explanations

    references to various types of fans and cooling devices

    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
     customers
    -0.74
    parsedMessage
    -0.71
     passengers
    -0.70
    providedIn
    -0.63
     visitors
    -0.63
    addGap
    -0.63
     clients
    -0.61
    SizeF
    -0.61
    ::-
    -0.59
    XtraBars
    -0.57
    POSITIVE LOGITS
     fan
    3.66
    Fan
    3.23
    fan
    3.17
     Fan
    3.08
     fans
    2.61
    FAN
    2.56
     FAN
    2.56
     Fans
    2.53
    fans
    2.48
    Fans
    2.39
    Activations Density 0.031%

    No Known Activations