© 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. 12164
    Prev
    Next
    INDEX
    Explanations

    descriptions of environmental sensations, particularly focusing on breezes or winds

    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
    tagPool
    -0.54
     виправивши
    -0.50
    HasAnnotation
    -0.49
     useParams
    -0.48
    ="@+
    -0.48
    ังก
    -0.48
    र्फ
    -0.48
    出場
    -0.47
     المعيارى
    -0.47
    بوابة
    -0.47
    POSITIVE LOGITS
    ticle
    0.91
     breeze
    0.90
    ########.
    0.89
    liosis
    0.87
    penes
    0.85
    unch
    0.83
    AutoScaleMode
    0.82
     lan
    0.79
    Gur
    0.77
    UNCH
    0.76
    Activations Density 0.048%

    No Known Activations