© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2175
    Prev
    Next
    INDEX
    Explanations

    Mesopo

    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
     mass
    -0.60
    Mass
    -0.56
     Mass
    -0.56
    umburg
    -0.55
     []:
    -0.55
     Masse
    -0.53
    mass
    -0.53
    door
    -0.52
     security
    -0.52
     deform
    -0.52
    POSITIVE LOGITS
    ptian
    0.56
    yntaxException
    0.55
     المعيارى
    0.54
     Rè
    0.49
    DJANGO
    0.48
     pancreatitis
    0.48
    tawesome
    0.48
     *)__
    0.46
     genoemd
    0.45
     Administrativna
    0.44
    Activations Density 0.000%

    No Known Activations