© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15164
    Prev
    Next
    INDEX
    Explanations

    the presence or forms of the verb "to be"

    oai_token-act-pair · gpt-4.1-nano
    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
    UnknownFieldSet
    -0.60
     with
    -0.53
     dedicated
    -0.46
     members
    -0.45
     Möglichkeit
    -0.45
    RTLD
    -0.45
    RESERVED
    -0.45
    MEMBERS
    -0.44
     inv
    -0.44
    тером
    -0.42
    POSITIVE LOGITS
    出版年
    0.76
     ſmall
    0.75
     itſelf
    0.75
    ].)
    0.73
    )|^{
    0.72
    ).)
    0.71
    χρι
    0.71
     Theſe
    0.71
    $_.
    0.70
     Drapeau
    0.70
    Activations Density 0.181%

    No Known Activations