© 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. 178
    Prev
    Next
    INDEX
    Explanations

    statements of research findings

    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
    RenderAtEndOf
    -0.93
    ValueStyle
    -0.80
    oa̍t
    -0.71
    another
    -0.69
    something
    -0.67
     another
    -0.64
    ModelAdmin
    -0.62
     something
    -0.62
    mybatisplus
    -0.60
    ISupport
    -0.60
    POSITIVE LOGITS
     considerable
    1.19
     great
    1.16
     tremendous
    1.16
     significant
    1.13
     strong
    1.08
     excellent
    1.08
     substantial
    1.02
     immense
    1.00
     high
    0.99
     enormous
    0.96
    Activations Density 3.757%

    No Known Activations