© 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. 94981
    Prev
    Next
    INDEX
    Explanations

    changes or movement

    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
     متعلقه
    -0.94
     Normdatei
    -0.92
     sceptre
    -0.91
     myrtle
    -0.87
     bershka
    -0.86
     typelib
    -0.86
     Esau
    -0.84
     ravine
    -0.84
     doubtnut
    -0.82
     martyrdom
    -0.82
    POSITIVE LOGITS
     er
    0.54
     ich
    0.53
     f
    0.53
     str
    0.53
     to
    0.52
     chi
    0.52
     U
    0.51
     z
    0.50
     Ad
    0.50
     el
    0.49
    Activations Density 0.105%

    No Known Activations