© 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. 3-RES-MATRYOSHKA-DC
    7. 133
    Prev
    Next
    INDEX
    Explanations

    discussions about different scenarios or specific examples

    oai_token-act-pair · gemini-2.0-flash
    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
     Monfieur
    -0.96
    #+#
    -0.84
     صوتيه
    -0.83
    Память
    -0.78
     ویکی‌آمباردا
    -0.74
     Theſe
    -0.74
     Metzger
    -0.73
     Mercurio
    -0.73
    AnchorStyles
    -0.72
    RetentionPolicy
    -0.71
    POSITIVE LOGITS
     case
    3.33
     cases
    3.06
    case
    3.02
     Case
    3.00
    Case
    2.91
     Cases
    2.78
     CASE
    2.73
    CASE
    2.70
    Cases
    2.64
    cases
    2.63
    Activations Density 0.782%

    No Known Activations