© 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. 24-RES-MATRYOSHKA-DC
    7. 497
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating a negative or critical tone or situation in a variety of topics, including politics, technology, and personal opinions.

    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.24.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.24.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
    beelding
    -0.67
    gehalt
    -0.63
    ISM
    -0.60
    ITY
    -0.60
    binaan
    -0.59
    ized
    -0.58
    IZE
    -0.57
    IZED
    -0.57
    ALLY
    -0.57
    ization
    -0.56
    POSITIVE LOGITS
    point
    0.91
    board
    0.88
    room
    0.87
    points
    0.86
    box
    0.84
    -
    0.84
    line
    0.83
    water
    0.80
    word
    0.79
    mark
    0.78
    Activations Density 6.286%

    No Known Activations