© 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. 22-RES-MATRYOSHKA-DC
    7. 8
    Prev
    Next
    INDEX
    Explanations

    structured references to figures, equations, and cited works in academic papers

    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
    EndGlobalSection
    -0.90
    */].
    -0.90
     "\<
    -0.84
     Diſ
    -0.83
     Houſe
    -0.83
    =$?
    -0.80
     $_"
    -0.79
     !_
    -0.79
     '/';
    -0.79
     &_
    -0.78
    POSITIVE LOGITS
     (
    3.02
    (
    2.13
    （
    1.66
     $(
    1.42
     ((
    1.30
     ($
    1.27
    ((
    1.24
    }(
    1.23
     （
    1.23
     [
    1.20
    Activations Density 7.407%

    No Known Activations