© 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. 1-RES-MATRYOSHKA-DC
    7. 836
    Prev
    Next
    INDEX
    Explanations

    references to the potential advantages or positive effects

    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
    lwjgl
    -0.53
    })()
    -0.50
     refus
    -0.47
    dious
    -0.47
    StyleSheet
    -0.47
    SerializeField
    -0.46
    riture
    -0.46
     Selva
    -0.46
    暂无
    -0.46
    setResizable
    -0.46
    POSITIVE LOGITS
     benefit
    4.63
    benefit
    4.19
     benefits
    4.16
     Benefit
    4.13
    Benefit
    4.09
     Benefits
    3.86
    benefits
    3.70
    Benefits
    3.55
     BENEFITS
    3.53
     BENE
    3.52
    Activations Density 0.797%

    No Known Activations