© 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. 20-CLT-HP
    7. 75413
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical language

    np_max-act-logits · 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
     supérieures
    -0.51
    Mutagenicity
    -0.45
     llamaba
    -0.44
     estábamos
    -0.43
     ejerc
    -0.43
    Incompatible
    -0.43
     godk
    -0.42
     kapcsol
    -0.41
     matéri
    -0.41
     dimenti
    -0.40
    POSITIVE LOGITS
    DockStyle
    0.79
     AttributeSet
    0.78
    enumii
    0.75
     POM
    0.75
    PropertyGroup
    0.72
    PhysRev
    0.71
    endphp
    0.69
     JpaRepository
    0.68
     kiss
    0.68
    ScopeManager
    0.65
    Activations Density 0.005%

    No Known Activations