© 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. 246
    Prev
    Next
    INDEX
    Explanations

    academic papers and scientific writing by keying in on language such as "studies" "been" "research" etc

    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
     متعلقه
    -0.70
     خارجية
    -0.60
     محفوظة
    -0.60
     olisi
    -0.55
    běh
    -0.54
     theirs
    -0.54
     صوتيه
    -0.53
     yours
    -0.53
    طيع
    -0.53
    irmanship
    -0.52
    POSITIVE LOGITS
     commonly
    1.68
     widely
    1.56
     popular
    1.52
     Commonly
    1.48
    commonly
    1.47
    popular
    1.46
     frequently
    1.44
     Widely
    1.38
     popularly
    1.31
     often
    1.30
    Activations Density 4.565%

    No Known Activations