© 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. 4-CLT-HP
    7. 1312
    Prev
    Next
    INDEX
    Explanations

    by

    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
    AccessFile
    -0.58
    MessageTagHelper
    -0.55
    VIAF
    -0.54
     VIAF
    -0.52
    OrNil
    -0.50
     Aven
    -0.50
     tartalomajánló
    -0.48
    WithEmail
    -0.48
    Captor
    -0.48
    Literatur
    -0.47
    POSITIVE LOGITS
    ltk
    0.62
    mbols
    0.54
    osamente
    0.54
     considérons
    0.53
     claimed
    0.52
     tanke
    0.52
     Turning
    0.52
     endforeach
    0.51
     turned
    0.51
     according
    0.51
    Activations Density 0.005%

    No Known Activations