© 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. 824
    Prev
    Next
    INDEX
    Explanations

    air

    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
    帖最后由
    -0.70
    хьтан
    -0.68
    webElementXpaths
    -0.65
    Bibliograf
    -0.63
     négatif
    -0.63
     GenerationType
    -0.62
     tromper
    -0.62
    ukses
    -0.61
     cromado
    -0.61
    Grüsse
    -0.61
    POSITIVE LOGITS
    KommentareTeilen
    0.54
     humidity
    0.46
     contains
    0.45
    Portale
    0.45
    ReusableCell
    0.44
    jal
    0.44
    getDoctrine
    0.43
     AttributeSet
    0.42
     in
    0.41
    borne
    0.40
    Activations Density 0.002%

    No Known Activations