© 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. 5-CLT-HP
    7. 97404
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    RenderAtEndOf
    -0.69
    uyasha
    -0.60
     محفوظة
    -0.58
    lgari
    -0.58
    /")
    -0.56
     actionMode
    -0.56
     ')
    -0.54
    };*/
    -0.53
    %
    -0.53
    Rüyada
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.74
    complexContent
    0.63
    inheritdoc
    0.60
    ChildScrollView
    0.56
     chi̍t
    0.54
    一行
    0.53
    udsman
    0.51
    disconnected
    0.50
     Couleur
    0.50
     Disp
    0.49
    Activations Density 0.000%

    No Known Activations