© 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. 18-RES-MATRYOSHKA-DC
    7. 1199
    Prev
    Next
    INDEX
    Explanations

    references to lists, explanations, or further information

    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/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.83
    PyExc
    -0.64
    featureID
    -0.63
    AlterField
    -0.63
    NameInMap
    -0.60
    OGND
    -0.58
    ]")]
    -0.58
    skjaer
    -0.57
    NUMX
    -0.57
    osto
    -0.54
    POSITIVE LOGITS
     click
    1.39
     CLICK
    1.34
     Click
    1.28
    click
    1.20
     please
    1.20
    Click
    1.19
     see
    1.17
    CLICK
    1.12
    See
    1.08
     klik
    1.07
    Activations Density 1.257%

    No Known Activations