© 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. 4-CLT-HP
    7. 135
    Prev
    Next
    INDEX
    Explanations

    post

    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
    ManagedBean
    -0.62
    ագրություններ
    -0.59
     Roskov
    -0.57
    writeFieldEnd
    -0.56
     GenerationType
    -0.53
    parseColor
    -0.52
    Infof
    -0.51
    stateProvider
    -0.50
     متعلقه
    -0.50
     Milestone
    -0.50
    POSITIVE LOGITS
    StructEnd
    0.61
    rativa
    0.49
    Transcription
    0.48
     representatives
    0.48
     picioare
    0.48
     mitotic
    0.47
    synthetic
    0.47
    Executives
    0.46
     myndig
    0.45
    mit
    0.44
    Activations Density 0.005%

    No Known Activations