© 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. 15650
    Prev
    Next
    INDEX
    Explanations

    Starting code/environments

    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
    parseFrom
    -0.52
    LabelTagHelper
    -0.46
     manqué
    -0.44
     eg
    -0.43
     brauche
    -0.40
     отношению
    -0.40
     داریم
    -0.40
    当た
    -0.40
     pan
    -0.40
     no
    -0.39
    POSITIVE LOGITS
    ArgsConstructor
    0.86
    findpost
    0.85
    исленность
    0.82
    الدراسه
    0.76
    GraphicsUnit
    0.71
    دانشنامهٔ
    0.70
    WriteAttribute
    0.69
    ChildScrollView
    0.69
    ollectionView
    0.66
    ougars
    0.66
    Activations Density 2.825%

    No Known Activations