© 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. 134
    Prev
    Next
    INDEX
    Explanations

    a mix of terms related to file installation, medical, folk tales, music, mathematics/engineering, and romance languages

    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
     doInBackground
    -0.84
    Jeografia
    -0.82
     Réponses
    -0.79
    PageContext
    -0.79
     Pute
    -0.77
     StringTokenizer
    -0.77
     Arzneimit
    -0.75
    — 
    -0.75
    ed
    -0.74
     BoxFit
    -0.74
    POSITIVE LOGITS
     Jol
    1.09
    lllll
    1.05
    lll
    1.00
    jal
    1.00
    al
    0.99
    llll
    0.98
    jil
    0.96
    Jol
    0.96
    kal
    0.96
    JAL
    0.96
    Activations Density 7.367%

    No Known Activations