© 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. 42405
    Prev
    Next
    INDEX
    Explanations

    Legal and technical documents

    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
     cala
    -1.02
    PCell
    -0.55
    acke
    -0.45
    FXML
    -0.44
    laka
    -0.42
     Pratt
    -0.42
     Appel
    -0.42
     Do
    -0.41
     Stop
    -0.40
     “
    -0.40
    POSITIVE LOGITS
     poffible
    0.94
     purpoſe
    0.88
     myſelf
    0.88
     himſelf
    0.85
     pleaſure
    0.84
     occaf
    0.82
     houſe
    0.81
     Efq
    0.79
     Monfieur
    0.79
     raiſ
    0.78
    Activations Density 1.233%

    No Known Activations