© 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. 98191
    Prev
    Next
    INDEX
    Explanations

    Relationships, connections

    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
    ValueStyle
    -0.88
     OnInit
    -0.79
    enumi
    -0.75
     CreateTagHelper
    -0.69
     препратки
    -0.68
    enumii
    -0.67
     архивлан
    -0.66
    anthene
    -0.66
     numberOfRows
    -0.66
    IntoConstraints
    -0.66
    POSITIVE LOGITS
    ,
    0.58
     Their
    0.51
     America
    0.49
     Its
    0.49
     all
    0.48
     успе
    0.48
    :
    0.46
    —
    0.45
     sound
    0.45
     —
    0.44
    Activations Density 0.000%

    No Known Activations