© 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. 5-CLT-HP
    7. 91270
    Prev
    Next
    INDEX
    Explanations

    podcast

    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
    ed
    -0.61
     "..\..\..\
    -0.59
    ete
    -0.58
     Unidas
    -0.52
    новниш
    -0.52
     "..\..\
    -0.52
    ized
    -0.51
    djangoproject
    -0.51
    alties
    -0.50
    ifa
    -0.49
    POSITIVE LOGITS
     nakalista
    0.65
    expandindo
    0.65
    الإنجليزية
    0.53
    Episodes
    0.53
     onPostExecute
    0.52
     Anfitrión
    0.52
     مشين
    0.51
    Transcription
    0.51
     doInBackground
    0.51
    ̈́
    0.50
    Activations Density 0.002%

    No Known Activations