© 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
    2. Gemma-2-2B
    3. 1-RES-MATRYOSHKA-DC
    4. 251
    Prev
    Next
    INDEX
    Explanations

    the presence of end-of-sequence or termination markers in the text

    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
     CURIAM
    -0.72
    vician
    -0.69
     препратки
    -0.60
    onomía
    -0.58
    Rüyada
    -0.57
    hilangan
    -0.56
    bootstrapcdn
    -0.56
    Referències
    -0.56
    rückt
    -0.53
    زش
    -0.52
    POSITIVE LOGITS
     end
    4.22
    end
    4.09
     End
    4.03
    End
    3.88
     END
    3.59
    END
    3.34
     ends
    2.84
    ends
    2.69
     Ends
    2.69
     ended
    2.44
    Activations Density 0.666%

    No Known Activations