© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 4460
    Prev
    Next
    INDEX
    Explanations

    magnetic

    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
     EconPapers
    -0.48
    icina
    -0.45
     phases
    -0.42
    +#+#
    -0.42
    localctx
    -0.40
    kirchen
    -0.40
    bulo
    -0.40
     prefix
    -0.38
    terase
    -0.38
    qrst
    -0.37
    POSITIVE LOGITS
    ."));
    0.91
    <bos>
    0.90
    )");
    
    0.86
     }}$}
    0.84
    horabuena
    0.83
    '}>
    0.83
    .}}
    0.82
    "}>
    0.80
    "});
    0.79
    "}}
    0.78
    Activations Density 0.122%

    No Known Activations