© 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. 3574
    Prev
    Next
    INDEX
    Explanations

    numerical values or parameters

    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
    ########.
    -0.94
     فريبيس
    -0.85
    DeleteBehavior
    -0.82
    UnusedPrivate
    -0.81
    bootstrapcdn
    -0.80
    IsContent
    -0.79
    ніципа
    -0.79
    Rohy
    -0.79
     समीक्षाओं
    -0.79
     JpaRepository
    -0.77
    POSITIVE LOGITS
     super
    0.44
    错
    0.42
     th
    0.40
     ir
    0.40
    DAD
    0.40
     "
    0.39
    錯
    0.39
    liffe
    0.39
    viere
    0.38
    Kaynak
    0.38
    Activations Density 0.113%

    No Known Activations