© 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. 22-RES-MATRYOSHKA-DC
    7. 1351
    Prev
    Next
    INDEX
    Explanations

    the word "water" and its derivatives

    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
    TestFixture
    -0.55
    fromnode
    -0.55
    specifier
    -0.52
    TextHelper
    -0.50
    ecap
    -0.50
    ineno
    -0.49
    anstalt
    -0.48
     totul
    -0.48
    Бахар
    -0.47
     []).
    -0.47
    POSITIVE LOGITS
    cress
    0.78
    logged
    0.76
    melons
    0.75
    borne
    0.72
    oluble
    0.66
     judiciaire
    0.64
    tight
    0.63
    courses
    0.63
    PROOF
    0.63
     vapour
    0.62
    Activations Density 0.334%

    No Known Activations