© 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. 5-CLT-HP
    7. 91989
    Prev
    Next
    INDEX
    Explanations

    sha

    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
    yelitis
    -0.56
    CompleteListener
    -0.54
    aarrggbb
    -0.54
     lenker
    -0.53
     SwitchCompat
    -0.53
    writeFieldEnd
    -0.52
     Scotty
    -0.50
    Filmographie
    -0.50
    FieldNumber
    -0.50
    ="@+
    -0.50
    POSITIVE LOGITS
    XmlAccessType
    0.58
    LookAnd
    0.57
    OH
    0.55
    MenuView
    0.52
     Dawes
    0.47
    SOUNDBITE
    0.45
    butter
    0.45
    KE
    0.45
    1
    0.44
    Js
    0.44
    Activations Density 0.001%

    No Known Activations