© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 69
    Prev
    Next
    INDEX
    Explanations

    technical writing, especially related to scientific publications or patents, using words like "distribution," "silencing," "reduce," "increasing," "degradation," and sensitivity."

    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
     pagado
    -0.68
     interesado
    -0.63
     hangat
    -0.59
     متعلقه
    -0.59
     recensione
    -0.56
     détruire
    -0.54
    หมือน
    -0.53
     réguli
    -0.52
     prende
    -0.50
    ibatis
    -0.50
    POSITIVE LOGITS
     effectiveness
    1.36
     efficiency
    1.24
     overall
    1.24
     ability
    1.20
     amount
    1.18
     performance
    1.18
     size
    1.17
     quality
    1.13
     accuracy
    1.13
     availability
    1.09
    Activations Density 9.575%

    No Known Activations