© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1184
    Prev
    Next
    INDEX
    Explanations

    assistance, usefulness, value

    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
    tvguidetime
    -0.55
    vsk
    -0.48
    costal
    -0.47
     memp
    -0.44
    ionView
    -0.42
    arh
    -0.41
     space
    -0.41
    Démographie
    -0.41
     she
    -0.40
    RunWith
    -0.40
    POSITIVE LOGITS
    verwijspagina
    0.78
     to
    0.77
     esternos
    0.73
    DebuggerNonUser
    0.68
     leſs
    0.68
    ſelves
    0.67
    BufferException
    0.66
    WireFormatLite
    0.66
     itſelf
    0.65
     newOwner
    0.64
    Activations Density 0.020%

    No Known Activations