© 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. 11335
    Prev
    Next
    INDEX
    Explanations

    geometric angles related to optical devices or measurement instruments

    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
    ANGLE
    -1.97
     Ang
    -1.69
    Ang
    -1.66
    ANG
    -1.66
    ang
    -1.55
     ang
    -1.48
     ANG
    -1.48
    angular
    -1.29
    angs
    -1.16
     angular
    -1.13
    POSITIVE LOGITS
     angle
    1.38
     Angle
    0.57
     ángulo
    0.54
     casera
    0.54
     ddelweddau
    0.53
     getopt
    0.53
     authentique
    0.51
     alimentare
    0.50
    JspWriter
    0.48
     sánh
    0.47
    Activations Density 0.004%

    No Known Activations