© 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. 31121
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and computing concepts

    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
     Theſe
    -0.97
     pleaſure
    -0.95
    ſelf
    -0.91
    ſelves
    -0.90
     becauſe
    -0.89
    IntoConstraints
    -0.89
     ainfi
    -0.88
     ſeveral
    -0.88
     Eſ
    -0.86
     Efq
    -0.85
    POSITIVE LOGITS
     mar
    0.48
     band
    0.44
     rub
    0.43
     Heb
    0.42
     most
    0.42
     Var
    0.41
     то
    0.41
     cut
    0.40
     lenker
    0.40
    uple
    0.40
    Activations Density 0.135%

    No Known Activations