© 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. 24-RES-MATRYOSHKA-DC
    7. 306
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms

    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.24.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.24.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
    AddTagHelper
    -0.82
    AndEndTag
    -0.77
    脚注の使い方
    -0.75
    windowFixed
    -0.70
    PullParser
    -0.63
     estekak
    -0.60
    LEEP
    -0.59
    曖昧さ回避
    -0.59
     actuelles
    -0.58
    帖最后由
    -0.57
    POSITIVE LOGITS
     that
    1.23
     containing
    1.09
     which
    1.09
     whose
    1.08
     capable
    1.03
     consisting
    1.01
     resembling
    0.93
     composed
    0.92
     designed
    0.90
     cuya
    0.88
    Activations Density 5.908%

    No Known Activations