© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11890
    Prev
    Next
    INDEX
    Explanations

    references to structural observations and data, particularly numerical or visual data about specific features

    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
     Observation
    -1.12
     observation
    -1.08
    Observation
    -0.93
    observation
    -0.85
     Normdatei
    -0.68
    UnusedPrivate
    -0.66
     Gelatin
    -0.63
     sagde
    -0.62
    odiment
    -0.59
     datas
    -0.59
    POSITIVE LOGITS
     observations
    1.20
    observations
    0.93
     Observations
    0.81
    Observations
    0.81
     OBSERVATIONS
    0.63
     observaciones
    0.60
    UVWXYZ
    0.59
     observers
    0.55
     Notes
    0.55
     notes
    0.53
    Activations Density 0.003%

    No Known Activations