© 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. 18-RES-MATRYOSHKA-DC
    7. 1091
    Prev
    Next
    INDEX
    Explanations

    the word "turn" with varying tenses and surrounding words

    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.18.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.18.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
    IntoConstraints
    -0.62
    makeConstraints
    -0.62
     rappel
    -0.54
     EVA
    -0.53
     aktivitet
    -0.52
    鰭
    -0.52
     pregă
    -0.52
     famí
    -0.52
     femininos
    -0.52
     richi
    -0.51
    POSITIVE LOGITS
     turn
    1.63
     Turn
    1.60
     TURN
    1.59
     turns
    1.58
    Turn
    1.55
    TURN
    1.54
     turned
    1.52
     turning
    1.50
    Turning
    1.48
    Turned
    1.48
    Activations Density 0.275%

    No Known Activations