© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5703
    Prev
    Next
    INDEX
    Explanations

    and

    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
    aarrggbb
    -0.70
    HasForeignKey
    -0.70
    +#+#
    -0.69
     ISNI
    -0.65
    enumi
    -0.64
    TestTools
    -0.61
    écnicas
    -0.60
     OnTriggerEnter
    -0.57
     even
    -0.56
    openSession
    -0.56
    POSITIVE LOGITS
     due
    0.49
    UGHTER
    0.47
    due
    0.45
     Frat
    0.45
     peace
    0.44
    progressDialog
    0.43
     maat
    0.42
     excellence
    0.42
     cosa
    0.42
    malink
    0.42
    Activations Density 0.001%

    No Known Activations