© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93142
    Prev
    Next
    INDEX
    Explanations

    Numbers and years

    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
     ویکی‌پدیای
    -0.56
    Véxase
    -0.47
     Malvern
    -0.46
    ulity
    -0.43
     ejus
    -0.42
     omnia
    -0.42
    XmlAccessType
    -0.41
     Shakspeare
    -0.40
     juſ
    -0.39
     kaarangay
    -0.39
    POSITIVE LOGITS
     Huy
    0.63
     AssemblyCompany
    0.61
    curity
    0.58
    quarters
    0.56
    guém
    0.55
    withIdentifier
    0.55
    värr
    0.55
    
    0.55
    <?
    0.55
     getPassword
    0.54
    Activations Density 0.000%

    No Known Activations