© 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. 1-CLT-HP
    7. 9124
    Prev
    Next
    INDEX
    Explanations

    ators

    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
    didSet
    -0.73
    
    -0.71
    EDEFAULT
    -0.71
    存于互联网档案馆
    -0.68
     ब्रेकडाउन
    -0.66
     myſelf
    -0.66
     المعيارى
    -0.66
     itſelf
    -0.65
    ponses
    -0.65
    #+#
    -0.65
    POSITIVE LOGITS
    irnov
    0.49
    FORC
    0.46
    splat
    0.45
    TabLayout
    0.45
     trå
    0.44
    ʊ
    0.44
    bukaan
    0.42
    bia
    0.42
    acing
    0.42
    板
    0.41
    Activations Density 0.033%

    No Known Activations