© 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. 4184
    Prev
    Next
    INDEX
    Explanations

    the capability or capacity to measure or assess a specific attribute or quality

    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
     MainAxisSize
    -0.65
     possíveis
    -0.62
     practicable
    -0.59
     possibles
    -0.59
     possível
    -0.58
    Possible
    -0.56
     Possible
    -0.55
     insuffisamment
    -0.55
     مشارکت‌کنندگان
    -0.55
     possible
    -0.54
    POSITIVE LOGITS
     ability
    2.53
     Ability
    2.17
    Ability
    2.03
     abilities
    1.99
     Abilities
    1.69
     Fähigkeit
    1.66
     capability
    1.63
     kemampuan
    1.48
    能力
    1.45
     capacidad
    1.37
    Activations Density 0.129%

    No Known Activations