© 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. 5-CLT-HP
    7. 92185
    Prev
    Next
    INDEX
    Explanations

    second person sentences

    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
    tvguidetime
    -0.74
     CreateTagHelper
    -0.66
     demografica
    -0.60
    CopyWith
    -0.58
    Begriffsklä
    -0.57
     BoxFit
    -0.57
    baguna
    -0.56
    ;#
    -0.56
    gelopen
    -0.56
    หมือน
    -0.56
    POSITIVE LOGITS
    AndEndTag
    0.57
     anything
    0.47
    どり
    0.46
    XmlAccessorType
    0.46
    DIPSETTING
    0.44
     change
    0.43
     culo
    0.43
    saveData
    0.43
    aving
    0.43
     net
    0.42
    Activations Density 0.000%

    No Known Activations