© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13700
    Prev
    Next
    INDEX
    Explanations

    sentences describing the primary purpose or goal of an activity or intervention

    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
     مشين
    -0.75
    harusnya
    -0.72
     indisponible
    -0.65
     springfox
    -0.65
     termica
    -0.63
    出版年
    -0.63
    ilíbrio
    -0.61
    numerusform
    -0.59
     célèbres
    -0.59
     élevées
    -0.59
    POSITIVE LOGITS
     e
    0.75
    tvguidetime
    0.58
     "'");
    0.57
    NoSuchAlgorithm
    0.54
    +");
    0.52
     pl
    0.51
    AllowAnonymous
    0.51
     i
    0.50
    }');
    0.50
    _();
    0.50
    Activations Density 0.034%

    No Known Activations