© 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. 91971
    Prev
    Next
    INDEX
    Explanations

    code release

    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
    ikasi
    -0.49
    Spoljašnje
    -0.48
     виправивши
    -0.48
     BoxFit
    -0.46
    MessageOf
    -0.46
    LookAnd
    -0.45
    iniu
    -0.42
    Composable
    -0.42
    odles
    -0.42
     sons
    -0.42
    POSITIVE LOGITS
    amitié
    0.57
    EReference
    0.56
    Hozzáférés
    0.53
    WHEREAS
    0.53
     NgModule
    0.53
    imageshack
    0.53
    CrossRef
    0.50
    श्न
    0.49
     betweenstory
    0.49
    UnsafeEnabled
    0.48
    Activations Density 0.001%

    No Known Activations