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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2710
    Prev
    Next
    INDEX
    Explanations

    Spatial relationships/sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JAMIN
    -0.58
    )"),
    -0.52
     ''}
    -0.50
    }")]
    -0.50
     }}">
    -0.50
    hematical
    -0.50
    })$}
    -0.50
     "..\..\
    -0.50
     />);
    -0.50
    }_{-
    -0.49
    POSITIVE LOGITS
    וויק
    0.60
     appunto
    0.56
     in
    0.55
    onOptions
    0.55
     to
    0.54
     تضيفلها
    0.54
    +#+#
    0.54
    جغرافيا
    0.52
     THOUGH
    0.52
     of
    0.52
    Activations Density 0.001%

    No Known Activations