© 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. 1514
    Prev
    Next
    INDEX
    Explanations

    code snippets containing the words 'in', 'to', 'from'

    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
    +#+#
    -0.59
    AddAttribute
    -0.53
     délic
    -0.49
     settings
    -0.49
    ---*/
    -0.49
    :+:
    -0.48
     <<<<<<<<<<<<<<
    -0.46
     copie
    -0.46
     peito
    -0.46
    nič
    -0.45
    POSITIVE LOGITS
     Microsoft
    0.78
     MATLAB
    0.74
     Matlab
    0.73
     Java
    0.71
     Python
    0.69
     WordPress
    0.65
     Adobe
    0.65
     jQuery
    0.65
     Android
    0.65
     Excel
    0.64
    Activations Density 1.794%

    No Known Activations