© 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. 5012
    Prev
    Next
    INDEX
    Explanations

    Dates, numbers, abbreviations

    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
    Scénario
    -0.51
    IComponent
    -0.51
    VersionUID
    -0.47
    ImageContext
    -0.46
    cases
    -0.45
    endola
    -0.45
    上角
    -0.45
    TabIndex
    -0.45
     endi
    -0.44
    ător
    -0.44
    POSITIVE LOGITS
    تقاوى
    0.74
    2
    0.61
    GEBURTSDATUM
    0.59
    1
    0.55
     Diss
    0.53
     Administrativna
    0.53
    rzez
    0.52
     WaitForSeconds
    0.52
    mybatisplus
    0.51
    PMailer
    0.51
    Activations Density 0.001%

    No Known Activations