© 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. 20-CLT-HP
    4. 76787
    Prev
    Next
    INDEX
    Explanations

    reporting verbs

    np_max-act-logits · 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
    .");
    -0.90
    .";
    -0.90
    "};
    -0.84
    ']));
    -0.83
    }";
    -0.83
    "]);
    -0.82
    ."),
    -0.82
    ']],
    -0.82
    "});
    -0.82
    "]}
    -0.82
    POSITIVE LOGITS
     citing
    0.63
     leading
    0.62
     indicating
    0.59
    Leading
    0.58
     stating
    0.58
     noting
    0.57
     considering
    0.56
     reflecting
    0.55
     knowing
    0.54
    leading
    0.53
    Activations Density 0.004%

    No Known Activations