© 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. 1-CLT-HP
    7. 10140
    Prev
    Next
    INDEX
    Explanations

    bacter

    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
    expandindo
    -0.67
     NSCoder
    -0.59
    FieldNumber
    -0.57
     takimi
    -0.52
    principalTable
    -0.52
    ripsi
    -0.52
     kasarigan
    -0.52
     StatusCode
    -0.51
    łady
    -0.51
    فيات
    -0.51
    POSITIVE LOGITS
     DbSet
    0.53
     CreateTagHelper
    0.53
     TestBed
    0.52
    ,_
    0.51
    AxisAlignment
    0.51
    bleau
    0.50
    astify
    0.49
    SPATH
    0.47
    issance
    0.46
    MeasureSpec
    0.46
    Activations Density 0.006%

    No Known Activations