© 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. 0-CLT-HP
    7. 95039
    Prev
    Next
    INDEX
    Explanations

    lae

    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
    ial
    -0.67
    ing
    -0.62
    ien
    -0.56
    EE
    -0.56
    Min
    -0.54
     Min
    -0.53
    iling
    -0.53
     Esc
    -0.53
    hila
    -0.53
    lae
    -0.52
    POSITIVE LOGITS
    RetentionPolicy
    0.68
     Theſe
    0.67
     Houſe
    0.65
     فريبيس
    0.55
     itſelf
    0.55
     themſelves
    0.52
     theſe
    0.51
     Anſ
    0.51
     ―――――
    0.51
     againſt
    0.50
    Activations Density 0.079%

    No Known Activations