© 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. 0-CLT-HP
    4. 94413
    Prev
    Next
    INDEX
    Explanations

    receptors

    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
     receptor
    -1.42
     receptors
    -1.34
     Receptor
    -1.25
     Receptors
    -1.16
     track
    -1.13
    receptor
    -1.10
     reception
    -0.98
     Track
    -0.97
    track
    -0.97
    Track
    -0.93
    POSITIVE LOGITS
    ed
    0.73
     насељу
    0.69
    ?')
    0.65
    NUMX
    0.62
    ."));
    0.62
     '\\;'
    0.60
    PMailer
    0.60
    });*/
    0.59
    }`).
    0.59
     "];
    0.59
    Activations Density 0.776%

    No Known Activations