© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3173
    Prev
    Next
    INDEX
    Explanations

    the prefix "mis-"

    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
    WebMethod
    -0.75
     שוליים
    -0.73
    printStackTrace
    -0.69
    sizeCache
    -0.69
    InjectMocks
    -0.69
    ThroughAttribute
    -0.66
    onAttach
    -0.64
    ecore
    -0.60
    PDOException
    -0.60
    ⓧ
    -0.60
    POSITIVE LOGITS
     mis
    3.22
    mis
    3.06
    Mis
    3.02
     Mis
    3.00
     MIS
    2.58
    MIS
    2.47
     mismatch
    1.59
     miscon
    1.57
     misread
    1.55
     miſ
    1.51
    Activations Density 0.031%

    No Known Activations