© 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. 2014
    Prev
    Next
    INDEX
    Explanations

    the usage of specific types and categories in a structured data format

    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
     Becken
    -0.84
    UnsafeEnabled
    -0.81
    ształ
    -0.79
    ceuticals
    -0.78
     AppBar
    -0.77
     Carrots
    -0.77
    örungen
    -0.75
     parcour
    -0.75
     nicio
    -0.73
     HomeComponent
    -0.73
    POSITIVE LOGITS
     Type
    1.50
     TYPE
    1.48
     types
    1.41
     getType
    1.35
     type
    1.34
     Types
    1.30
    TYPE
    1.23
    types
    1.20
     tipo
    1.19
     tipos
    1.17
    Activations Density 0.492%

    No Known Activations