© 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. 5444
    Prev
    Next
    INDEX
    Explanations

    even

    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
    -0.68
    bilirsiniz
    -0.58
    enumi
    -0.58
    enumii
    -0.56
    entrion
    -0.56
     íntegra
    -0.54
     préfé
    -0.54
    alerie
    -0.54
     enfans
    -0.53
     skiers
    -0.52
    POSITIVE LOGITS
     triggering
    0.56
     inducing
    0.55
     causing
    0.55
     elic
    0.54
     turning
    0.54
     reaching
    0.50
    Cyfeiriadau
    0.50
     resulting
    0.50
    rupt
    0.49
     constituting
    0.48
    Activations Density 0.008%

    No Known Activations