© 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. 12-RES-MATRYOSHKA-DC
    7. 22913
    Prev
    Next
    INDEX
    Explanations

    specific sections or labels typically found in scientific papers or documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Soft
    -0.46
     verlassen
    -0.44
    PageState
    -0.44
    Be
    -0.44
    he
    -0.43
     Soft
    -0.41
    Bend
    -0.40
     soft
    -0.40
     ingenting
    -0.40
     glasses
    -0.40
    POSITIVE LOGITS
     autorytatywna
    1.11
    expandindo
    1.03
    +#+
    0.99
    évaluateur
    0.92
    LookAnd
    0.89
     CreateTagHelper
    0.89
     <=",
    0.89
     समीक्षक
    0.88
    NgModule
    0.88
    Autoritní
    0.87
    Activations Density 0.005%

    No Known Activations