© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93698
    Prev
    Next
    INDEX
    Explanations

    amnesia

    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
     El
    -0.56
    ,
    -0.52
     on
    -0.51
     di
    -0.51
     Get
    -0.51
     E
    -0.50
     sa
    -0.50
     bro
    -0.50
     U
    -0.50
     d
    -0.49
    POSITIVE LOGITS
     ainfi
    1.19
     feroit
    1.14
     Monfieur
    1.13
     raiſ
    1.12
     avoient
    1.05
     étoit
    1.04
     quæ
    1.03
     enfans
    1.03
     ſeveral
    1.03
     chré
    1.02
    Activations Density 0.411%

    No Known Activations