© 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. 18-RES-MATRYOSHKA-DC
    7. 895
    Prev
    Next
    INDEX
    Explanations

    patterns like "&ltnewline>number"

    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.18.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.18.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
     EAP
    -0.53
    ″]
    -0.52
     AIM
    -0.48
     deported
    -0.47
     COS
    -0.47
     Terraria
    -0.46
     kartą
    -0.45
     Ehr
    -0.45
    mok
    -0.44
     knots
    -0.44
    POSITIVE LOGITS
    :✨
    0.79
    ngdoc
    0.78
    LookAnd
    0.78
    AlterField
    0.65
    تقاوى
    0.62
    StoryboardSegue
    0.62
    帖最后由
    0.59
    webElementGuid
    0.59
     remaining
    0.58
    NamedQueries
    0.58
    Activations Density 0.460%

    No Known Activations