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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 172
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    aarrggbb
    -0.57
     oleo
    -0.54
    FormState
    -0.52
     noastre
    -0.52
     Juventus
    -0.49
     unavoid
    -0.49
    cleros
    -0.48
     Bibi
    -0.47
     fondant
    -0.47
     Shallow
    -0.47
    POSITIVE LOGITS
    principalTable
    0.73
     snippetHide
    0.66
    brainly
    0.65
     ]
    0.65
    ']))
    0.63
    Население
    0.59
    '))
    0.58
    makeConstraints
    0.58
    '));
    0.57
    setViewName
    0.57
    Activations Density 0.005%

    No Known Activations