© 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. 20-CLT-HP
    7. 71954
    Prev
    Next
    INDEX
    Explanations

    Code and formal language

    np_max-act-logits · 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
    ValueStyle
    -0.60
    marginHorizontal
    -0.55
    onViewCreated
    -0.52
    paddingVertical
    -0.51
    alignSelf
    -0.51
     Tema
    -0.50
     صوتيه
    -0.50
    horabuena
    -0.49
     aught
    -0.49
     Réponses
    -0.49
    POSITIVE LOGITS
    webElementXpaths
    0.68
    IsMutable
    0.60
    SerializedSize
    0.58
    rawDesc
    0.54
    θεν
    0.52
     Ab
    0.49
    exp
    0.49
    Msp
    0.49
     Op
    0.48
    MergeFrom
    0.47
    Activations Density 0.000%

    No Known Activations