© 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. 0-RES-MATRYOSHKA-DC
    7. 15149
    Prev
    Next
    INDEX
    Explanations

    mentions of flaws or mistakes

    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
     shortcomings
    -0.92
     CURIAM
    -0.76
    __":
    -0.71
     deficiencies
    -0.69
     linkovi
    -0.68
    Filmographie
    -0.66
     sumpay
    -0.64
     bucket
    -0.61
     otomatig
    -0.61
     OCCUP
    -0.60
    POSITIVE LOGITS
     flaw
    2.00
     flaws
    1.44
     flawed
    1.22
     flawless
    1.15
    airo
    0.79
     flawlessly
    0.79
     Blas
    0.72
    Blas
    0.65
    dele
    0.64
    fla
    0.61
    Activations Density 0.001%

    No Known Activations