© 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. 1-CLT-HP
    7. 9794
    Prev
    Next
    INDEX
    Explanations

    9

    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
     
    -0.56
    9
    -0.55
    3
    -0.55
    5
    -0.54
    4
    -0.52
    2
    -0.50
    1
    -0.49
    8
    -0.49
    7
    -0.47
    6
    -0.46
    POSITIVE LOGITS
     itſelf
    1.27
    Geplaatst
    1.15
     myſelf
    1.11
    __":
    1.10
    contentLoaded
    1.09
     raiſ
    1.05
     виправивши
    1.03
     Monfieur
    1.02
     uſed
    1.02
     Efq
    1.02
    Activations Density 0.062%

    No Known Activations