© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29992
    Prev
    Next
    INDEX
    Explanations

    the word "light" and related terms like "illumination" and "source".

    oai_token-act-pair · gemini-2.0-flash
    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
    Lumin
    -0.66
     illuminating
    -0.65
     pleaſure
    -0.63
    Newspaper
    -0.62
    ftances
    -0.62
     Lumin
    -0.62
     illuminates
    -0.60
     igång
    -0.60
     Lamps
    -0.60
    Shadows
    -0.60
    POSITIVE LOGITS
    /*
    0.71
     MonoBehaviour
    0.65
    VolleyError
    0.60
    putin
    0.59
    antMatchers
    0.59
     المعيارى
    0.57
    preventDefault
    0.56
    toPromise
    0.56
    yargs
    0.56
    trecht
    0.55
    Activations Density 0.013%

    No Known Activations