Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14668
    Prev
    Next
    INDEX
    Explanations

    instructions, suggestions, and information related to technical or software development tasks

    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
     EDIT
    -1.13
    +#+#
    -0.89
    StructEnd
    -0.78
     vPvB
    -0.77
     Normdatei
    -0.75
     iprot
    -0.72
     disambiguazione
    -0.69
    __*/
    -0.69
    ]")]
    -0.69
    uxxxx
    -0.68
    POSITIVE LOGITS
    Edit
    1.67
     Edit
    1.27
    Permalink
    0.67
    Bearbeiten
    0.63
    gefü
    0.54
     Vle
    0.52
    Editar
    0.52
    Modifica
    0.52
     Shreve
    0.52
    NSE
    0.51
    Activations Density 0.001%

    No Known Activations