© 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. 2-RES-MATRYOSHKA-DC
    7. 3122
    Prev
    Next
    INDEX
    Explanations

    references to scientific figures or visual data representations

    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
     defaultstate
    -0.65
     ['',
    -0.56
    sizeCache
    -0.52
     venuto
    -0.52
    StoryboardSegue
    -0.51
    findpost
    -0.50
    AutoScaleMode
    -0.49
     كومونز
    -0.49
     ReSharper
    -0.47
    ftagPool
    -0.46
    POSITIVE LOGITS
    ]--;
    0.66
    ])]
    0.64
     <=",
    0.63
    }}^
    0.62
    }})
    0.61
    ագրություններ
    0.61
    CharStream
    0.61
    NUMX
    0.60
    èlement
    0.60
    )__
    0.60
    Activations Density 0.099%

    No Known Activations