© 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. 4825
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     avancée
    -0.60
     dépenses
    -0.56
     conséquences
    -0.55
     tecnológicos
    -0.55
     fondation
    -0.54
     thèmes
    -0.54
     conséquence
    -0.54
     años
    -0.53
    "]();
    -0.53
     Diakses
    -0.53
    POSITIVE LOGITS
    RenderAtEndOf
    0.59
    Personendaten
    0.58
    MLLoader
    0.57
    msgTypes
    0.56
    ValueStyle
    0.54
     <<<<<<<<<<<<<<
    0.54
     climbers
    0.54
    oredCriteria
    0.52
    SpringBootTest
    0.51
    InputBorder
    0.50
    Activations Density 0.018%

    No Known Activations