© 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. 5300
    Prev
    Next
    INDEX
    Explanations

    enough

    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
     jsPsych
    -0.59
    Personendaten
    -0.59
    lottesville
    -0.57
     فإن
    -0.54
    vänt
    -0.53
     thì
    -0.53
    ığında
    -0.52
    ffekt
    -0.50
     satunya
    -0.50
     fossero
    -0.50
    POSITIVE LOGITS
     lenker
    0.61
    存于互联网档案馆
    0.57
    ImageContext
    0.48
     Grounds
    0.48
    labelledby
    0.47
    Caso
    0.47
    OGND
    0.44
     Hopefully
    0.44
     Helmholtz
    0.44
     hopefully
    0.43
    Activations Density 0.017%

    No Known Activations