© 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. 97297
    Prev
    Next
    INDEX
    Explanations

    varied text snippets and/or code

    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
     contextLoads
    -0.56
    IUrlHelper
    -0.55
    InvalidProtocol
    -0.52
    WriteBarrier
    -0.50
    ModelForm
    -0.48
     jadx
    -0.47
     nonatomic
    -0.47
     HasFactory
    -0.44
    viewDidLoad
    -0.43
     ribs
    -0.43
    POSITIVE LOGITS
     Administrativna
    0.55
     jogja
    0.53
    seits
    0.53
    lamabad
    0.53
    ghalaya
    0.52
    batore
    0.52
     somewhere
    0.50
     Lake
    0.50
     Turquie
    0.50
    RenderAtEndOf
    0.50
    Activations Density 0.000%

    No Known Activations