© 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. 0-CLT-HP
    7. 94244
    Prev
    Next
    INDEX
    Explanations

    of, were

    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
    róleo
    -0.43
    ooker
    -0.37
     polio
    -0.36
     asesinado
    -0.36
     going
    -0.35
    BeginInit
    -0.35
    iVar
    -0.33
     TreeNode
    -0.32
     gasolina
    -0.32
    JTextField
    -0.32
    POSITIVE LOGITS
     consultato
    0.75
    >{@
    0.71
    ItemBackground
    0.71
    AutoScaleMode
    0.71
     Theſe
    0.69
    Those
    0.69
    nicamente
    0.68
    ❋
    0.68
    those
    0.67
     invokingState
    0.66
    Activations Density 0.103%

    No Known Activations