© 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. 9100
    Prev
    Next
    INDEX
    Explanations

    cereals, hematological

    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
    +#+#
    -0.84
    TagMode
    -0.71
    TemporalType
    -0.65
     EconPapers
    -0.63
    ChildScrollView
    -0.63
    UIControlState
    -0.63
     Sob
    -0.63
    httphttps
    -0.61
    gdx
    -0.60
     configureStore
    -0.59
    POSITIVE LOGITS
    ThroughAttribute
    0.48
    ]}>
    0.44
     Horn
    0.43
    {?>
    0.42
     Tri
    0.42
     propOrder
    0.42
     Char
    0.42
    Horn
    0.40
    Carriera
    0.40
    minY
    0.40
    Activations Density 0.007%

    No Known Activations