© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1008
    Prev
    Next
    INDEX
    Explanations

    references or citations in scientific writing

    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
    _
    -0.52
    -
    -0.50
    .
    -0.48
    ↵↵
    -0.47
    ,
    -0.45
    ↵
    -0.44
    зон
    -0.44
     pro
    -0.44
    以
    -0.44
    @
    -0.42
    POSITIVE LOGITS
     ProtoMessage
    1.20
     CreateTagHelper
    1.14
    MigrationBuilder
    1.12
    +#+
    1.08
    ConstraintMaker
    1.04
     <=",
    1.01
    MemoryWarning
    1.00
     lenker
    0.98
     NSCoder
    0.98
     myſelf
    0.96
    Activations Density 0.211%

    No Known Activations