Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95413
    Prev
    Next
    INDEX
    Explanations

    locations and buildings

    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
     OMITBAD
    -0.64
    OGND
    -0.51
    CloseOperation
    -0.50
    SequentialGroup
    -0.44
    NgModule
    -0.41
     estekak
    -0.41
     Exactos
    -0.41
    OneToMany
    -0.41
    jenost
    -0.41
     moule
    -0.40
    POSITIVE LOGITS
    currentColor
    0.63
     reaſon
    0.62
    __":
    0.62
    PSL
    0.61
    MessageState
    0.61
     Kaisers
    0.60
     Kenyatta
    0.60
     Hackney
    0.60
     Galilee
    0.59
    tableFuture
    0.59
    Activations Density 0.004%

    No Known Activations