© 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. 3-RES-MATRYOSHKA-DC
    7. 1475
    Prev
    Next
    INDEX
    Explanations

    the phrase "close 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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InitVars
    -0.63
    multer
    -0.63
     määrä
    -0.62
    CWE
    -0.58
    hagy
    -0.54
     aufnehmen
    -0.54
    Override
    -0.54
    wts
    -0.53
    tiéndose
    -0.53
    jsoup
    -0.52
    POSITIVE LOGITS
     close
    2.59
     Close
    2.27
     near
    2.25
    close
    2.19
     CLOSE
    2.19
     closer
    2.16
     Near
    2.16
    near
    2.13
     NEAR
    2.13
    Near
    2.11
    Activations Density 0.660%

    No Known Activations