© 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. 14355
    Prev
    Next
    INDEX
    Explanations

    references to the intensity of a light source, particularly emphasizing the word "light" and its associated strength level

    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
    neſs
    -0.74
    nefs
    -0.69
    Vidite
    -0.68
    Παραπομπές
    -0.63
     مؤرشف
    -0.61
     كومونز
    -0.61
     obstante
    -0.60
    PhysRev
    -0.59
    zzleHttp
    -0.59
    KommentareTeilen
    -0.58
    POSITIVE LOGITS
    light
    2.03
    lights
    1.34
    LIGHT
    0.96
    lighted
    0.93
    lite
    0.83
    lighting
    0.81
    ligh
    0.81
    LIGHTS
    0.78
    IGHT
    0.61
    lig
    0.60
    Activations Density 0.002%

    No Known Activations