© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15356
    Prev
    Next
    INDEX
    Explanations

    the core idea of emphasizing or highlighting the importance of points

    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
     points
    -1.59
    points
    -1.43
    Points
    -1.39
     Points
    -1.36
     POINTS
    -1.31
    POINTS
    -1.16
     pts
    -1.13
     Punkte
    -1.00
     punten
    -0.99
     Punkten
    -0.99
    POSITIVE LOGITS
    |]
    0.73
     point
    0.65
    \{\\
    0.62
    ']],
    0.61
    })]
    0.60
    pito
    0.57
    ))]
    0.57
     decade
    0.56
    ')),
    0.56
    ]";
    0.54
    Activations Density 0.015%

    No Known Activations