© 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. 2004
    Prev
    Next
    INDEX
    Explanations

    names of objects or materials

    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
     hit
    -0.56
    tista
    -0.53
     I
    -0.53
     '
    -0.52
     …
    -0.50
     space
    -0.50
    }());
    -0.50
     cue
    -0.50
     Forrest
    -0.50
     carbon
    -0.49
    POSITIVE LOGITS
    ItemBackground
    0.88
    Personendaten
    0.87
     earphone
    0.87
     stiefel
    0.84
     parasol
    0.84
     ashtray
    0.82
    MessageTagHelper
    0.82
     AssemblyCulture
    0.82
     easel
    0.82
    enumi
    0.80
    Activations Density 2.083%

    No Known Activations