© 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. 1-CLT-HP
    7. 12385
    Prev
    Next
    INDEX
    Explanations

    blob

    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
     blob
    -0.85
     hotels
    -0.77
     كومونز
    -0.76
     hotel
    -0.75
     متعلقه
    -0.75
    
    -0.73
    aarrggbb
    -0.73
     blobs
    -0.69
    didReceive
    -0.67
    يكب
    -0.66
    POSITIVE LOGITS
    p
    0.54
    g
    0.53
    o
    0.52
    us
    0.50
    self
    0.49
    Self
    0.47
    mstyle
    0.47
    ty
    0.47
    catch
    0.46
     italic
    0.46
    Activations Density 0.008%

    No Known Activations