© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2382
    Prev
    Next
    INDEX
    Explanations

    computer code/documentation

    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
    URLException
    -0.54
    upe
    -0.52
     Dot
    -0.51
    תו
    -0.51
     UnityEngine
    -0.50
     Pom
    -0.48
    ThemeOverlay
    -0.48
    SuppressLint
    -0.47
     rom
    -0.47
    eqn
    -0.47
    POSITIVE LOGITS
    évaluateur
    0.70
     مشين
    0.70
     ligiloj
    0.64
    PerformLayout
    0.61
    HomeAsUpEnabled
    0.59
    __':
    0.58
     pinulongan
    0.58
     Signalez
    0.56
    DockStyle
    0.53
    brainly
    0.52
    Activations Density 0.000%

    No Known Activations