© 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. 91537
    Prev
    Next
    INDEX
    Explanations

    Technical language/code/legal

    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
    TestingModule
    -0.56
    almo
    -0.53
    banded
    -0.52
    enderror
    -0.51
    BAND
    -0.50
     genética
    -0.49
    hand
    -0.49
     eletrônico
    -0.49
    yaf
    -0.49
    이블
    -0.49
    POSITIVE LOGITS
    URLException
    0.59
    Bronnen
    0.57
    sidemargin
    0.56
    Personendaten
    0.56
     WebDriverWait
    0.55
    XmlAccessorType
    0.55
     دیکھیے
    0.55
    :\/\/
    0.51
     causes
    0.50
     Qual
    0.50
    Activations Density 0.000%

    No Known Activations