© 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. 22-RES-MATRYOSHKA-DC
    7. 2671
    Prev
    Next
    INDEX
    Explanations

    numbers with a period

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    ⓧ
    -0.97
    CloseOperation
    -0.82
    verwijspagina
    -0.71
     CURIAM
    -0.68
    </caption>
    -0.63
    SequentialGroup
    -0.63
     disambiguazione
    -0.63
    EndContext
    -0.62
     unknownFields
    -0.62
    liceerd
    -0.59
    POSITIVE LOGITS
    1
    1.41
    2
    1.38
    5
    1.35
    3
    1.34
    4
    1.30
    6
    1.27
    7
    1.22
    8
    1.20
    9
    1.20
    0
    1.12
    Activations Density 1.471%

    No Known Activations