© 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. 4-CLT-HP
    7. 1005
    Prev
    Next
    INDEX
    Explanations

    family members

    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
    Preheat
    -0.51
     excav
    -0.48
    ))^{
    -0.47
    ficial
    -0.47
    erle
    -0.46
    inescent
    -0.46
     bè
    -0.46
    Ắ
    -0.45
     forerunner
    -0.45
    oluble
    -0.45
    POSITIVE LOGITS
     who
    0.91
    bootstrapcdn
    0.67
     tartalomajánló
    0.65
     &___
    0.59
    GEBURTSDATUM
    0.59
    TestBed
    0.59
    who
    0.59
     whom
    0.58
     whose
    0.57
     quien
    0.57
    Activations Density 0.014%

    No Known Activations