© 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. 22-RES-MATRYOSHKA-DC
    7. 2819
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about nature, including the articles "the" and "a" that often introduce them.

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.60
     Emits
    -0.52
    hrungen
    -0.47
     hiểm
    -0.46
     coast
    -0.45
     habitable
    -0.44
    Amicalement
    -0.44
    amoan
    -0.43
    oltán
    -0.43
     dangerous
    -0.43
    POSITIVE LOGITS
     sun
    0.85
     sky
    0.85
     sunshine
    0.81
     suns
    0.79
     breeze
    0.79
     air
    0.79
    SharedCtor
    0.78
     sunset
    0.77
     sunlight
    0.77
     clouds
    0.74
    Activations Density 0.140%

    No Known Activations