© 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. 2-RES-MATRYOSHKA-DC
    7. 4369
    Prev
    Next
    INDEX
    Explanations

    references to objective standards or criteria

    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
    存于互联网档案馆
    -1.14
    +:+
    -0.87
    bootstrapcdn
    -0.85
     subject
    -0.83
    WebVitals
    -0.82
    abestanden
    -0.79
     hopes
    -0.76
    IntoConstraints
    -0.76
    makeConstraints
    -0.75
     Subject
    -0.74
    POSITIVE LOGITS
     objective
    2.33
    objective
    2.25
     Objective
    2.06
    Objective
    1.95
     OBJECTIVE
    1.70
     objectively
    1.57
    OBJECTIVE
    1.45
    objec
    1.30
     objectivity
    1.24
     Objec
    1.14
    Activations Density 0.023%

    No Known Activations