© 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. 2712
    Prev
    Next
    INDEX
    Explanations

    the phrase "want to"

    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
     magát
    -0.63
     InputDecoration
    -0.63
     Signalez
    -0.57
     disambiguazione
    -0.56
    scriptcase
    -0.55
    plet
    -0.55
    InstrumentedTest
    -0.54
     Roskov
    -0.53
     سكانية
    -0.53
    '][$
    -0.53
    POSITIVE LOGITS
     know
    1.02
     knows
    0.87
     hear
    0.84
    know
    0.82
     graag
    0.81
    Know
    0.79
     hears
    0.74
     weten
    0.74
    hear
    0.73
     wissen
    0.73
    Activations Density 0.163%

    No Known Activations