© 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. 1-CLT-HP
    7. 15274
    Prev
    Next
    INDEX
    Explanations

    chemical

    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
    contentLoaded
    -0.89
     виправивши
    -0.71
    StructEnd
    -0.71
    osoba
    -0.68
     jScrollPane
    -0.65
    AndEndTag
    -0.65
     SwitchCompat
    -0.63
    +#+#
    -0.63
    shadowOpacity
    -0.62
     MainAxisSize
    -0.61
    POSITIVE LOGITS
     action
    0.64
    RetentionPolicy
    0.52
     affinities
    0.50
    action
    0.47
    AccessException
    0.47
     combination
    0.46
     integration
    0.44
     Action
    0.44
    Enlaces
    0.43
    PCell
    0.43
    Activations Density 0.017%

    No Known Activations